def test_is_keras_tensor(self):
for K in [KTH, KTF]:
np_var = np.array([1, 2])
try:
K.is_keras_tensor(np_var)
assert True is False
except ValueError:
# This is the expected behavior
continue
keras_var = K.variable(np_var)
assert K.is_keras_tensor(keras_var) is True
keras_placeholder = K.placeholder(shape=(2, 4, 5))
assert K.is_keras_tensor(keras_placeholder) is True
def __call__(self, inputs, initial_state=None, constants=None, **kwargs):
inputs, initial_state, constants = self._standardize_args(
inputs, initial_state, constants, self._num_constants)
if initial_state is None and constants is None:
return super(ExternalAttentionRNNWrapper, self).__call__(inputs, **kwargs)
# If any of `initial_state` or `constants` are specified and are Keras
# tensors, then add them to the inputs and temporarily modify the
# input_spec to include them.
additional_inputs = []
additional_specs = []
if initial_state is not None:
kwargs['initial_state'] = initial_state
additional_inputs += initial_state
self.state_spec = [InputSpec(shape=K.int_shape(state))
for state in initial_state]
additional_specs += self.state_spec
if constants is not None:
kwargs['constants'] = constants
additional_inputs += constants
self.constants_spec = [InputSpec(shape=K.int_shape(constant))
for constant in constants]
self._num_constants = len(constants)
additional_specs += self.constants_spec
# at this point additional_inputs cannot be empty
is_keras_tensor = K.is_keras_tensor(additional_inputs[0])
for tensor in additional_inputs:
if K.is_keras_tensor(tensor) != is_keras_tensor:
raise ValueError('The initial state or constants of an ExternalAttentionRNNWrapper'
' layer cannot be specified with a mix of'
' Keras tensors and non-Keras tensors'
' (a "Keras tensor" is a tensor that was'
' returned by a Keras layer, or by `Input`)')
if is_keras_tensor:
# Compute the full input spec, including state and constants
full_input = inputs + additional_inputs
full_input_spec = self.input_spec + additional_specs
# Perform the call with temporarily replaced input_spec
original_input_spec = self.input_spec
self.input_spec = full_input_spec
output = super(ExternalAttentionRNNWrapper, self).__call__(full_input, **kwargs)
self.input_spec = self.input_spec[:len(original_input_spec)]
return output
else:
return super(ExternalAttentionRNNWrapper, self).__call__(inputs, **kwargs)
def get_dilation_model_camvid(input_shape, apply_softmax, input_tensor, classes):
if input_tensor is None:
model_in = Input(shape=input_shape)
else:
if not K.is_keras_tensor(input_tensor):
model_in = Input(tensor=input_tensor, shape=input_shape)
else:
model_in = input_tensor
h = Convolution2D(64, 3, 3, activation='relu', name='conv1_1')(model_in)
h = Convolution2D(64, 3, 3, activation='relu', name='conv1_2')(h)
h = MaxPooling2D(pool_size=(2, 2), strides=(2, 2), name='pool1')(h)
h = Convolution2D(128, 3, 3, activation='relu', name='conv2_1')(h)
h = Convolution2D(128, 3, 3, activation='relu', name='conv2_2')(h)
h = MaxPooling2D(pool_size=(2, 2), strides=(2, 2), name='pool2')(h)
h = Convolution2D(256, 3, 3, activation='relu', name='conv3_1')(h)
h = Convolution2D(256, 3, 3, activation='relu', name='conv3_2')(h)
h = Convolution2D(256, 3, 3, activation='relu', name='conv3_3')(h)
h = MaxPooling2D(pool_size=(2, 2), strides=(2, 2), name='pool3')(h)
h = Convolution2D(512, 3, 3, activation='relu', name='conv4_1')(h)
h = Convolution2D(512, 3, 3, activation='relu', name='conv4_2')(h)
h = Convolution2D(512, 3, 3, activation='relu', name='conv4_3')(h)
h = AtrousConvolution2D(512, 3, 3, atrous_rate=(2, 2), activation='relu', name='conv5_1')(h)
h = AtrousConvolution2D(512, 3, 3, atrous_rate=(2, 2), activation='relu', name='conv5_2')(h)
h = AtrousConvolution2D(512, 3, 3, atrous_rate=(2, 2), activation='relu', name='conv5_3')(h)
h = AtrousConvolution2D(4096, 7, 7, atrous_rate=(4, 4), activation='relu', name='fc6')(h)
h = Dropout(0.5, name='drop6')(h)
h = Convolution2D(4096, 1, 1, activation='relu', name='fc7')(h)
h = Dropout(0.5, name='drop7')(h)
h = Convolution2D(classes, 1, 1, name='final')(h)
h = ZeroPadding2D(padding=(1, 1))(h)
h = Convolution2D(classes, 3, 3, activation='relu', name='ctx_conv1_1')(h)
h = ZeroPadding2D(padding=(1, 1))(h)
h = Convolution2D(classes, 3, 3, activation='relu', name='ctx_conv1_2')(h)
h = ZeroPadding2D(padding=(2, 2))(h)
h = AtrousConvolution2D(classes, 3, 3, atrous_rate=(2, 2), activation='relu', name='ctx_conv2_1')(h)
h = ZeroPadding2D(padding=(4, 4))(h)
h = AtrousConvolution2D(classes, 3, 3, atrous_rate=(4, 4), activation='relu', name='ctx_conv3_1')(h)
h = ZeroPadding2D(padding=(8, 8))(h)
h = AtrousConvolution2D(classes, 3, 3, atrous_rate=(8, 8), activation='relu', name='ctx_conv4_1')(h)
h = ZeroPadding2D(padding=(16, 16))(h)
h = AtrousConvolution2D(classes, 3, 3, atrous_rate=(16, 16), activation='relu', name='ctx_conv5_1')(h)
h = ZeroPadding2D(padding=(1, 1))(h)
h = Convolution2D(classes, 3, 3, activation='relu', name='ctx_fc1')(h)
logits = Convolution2D(classes, 1, 1, name='ctx_final')(h)
if apply_softmax:
model_out = softmax(logits)
else:
model_out = logits
model = Model(input=model_in, output=model_out, name='dilation_camvid')
return model
def nn_base(input_tensor=None, trainable=False):
# Determine proper input shape
if K.image_dim_ordering() == 'th':
input_shape = (3, None, None)
else:
input_shape = (None, None, 3)
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
if not K.is_keras_tensor(input_tensor):
img_input = Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
if K.image_dim_ordering() == 'tf':
bn_axis = 3
else:
bn_axis = 1
# Block 1
x = Conv2D(64, (3, 3), activation='relu', padding='same', name='block1_conv1')(img_input)
x = Conv2D(64, (3, 3), activation='relu', padding='same', name='block1_conv2')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='block1_pool')(x)
# Block 2
x = Conv2D(128, (3, 3), activation='relu', padding='same', name='block2_conv1')(x)
x = Conv2D(128, (3, 3), activation='relu', padding='same', name='block2_conv2')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='block2_pool')(x)
# Block 3
x = Conv2D(256, (3, 3), activation='relu', padding='same', name='block3_conv1')(x)
x = Conv2D(256, (3, 3), activation='relu', padding='same', name='block3_conv2')(x)
x = Conv2D(256, (3, 3), activation='relu', padding='same', name='block3_conv3')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='block3_pool')(x)
# Block 4
x = Conv2D(512, (3, 3), activation='relu', padding='same', name='block4_conv1')(x)
x = Conv2D(512, (3, 3), activation='relu', padding='same', name='block4_conv2')(x)
x = Conv2D(512, (3, 3), activation='relu', padding='same', name='block4_conv3')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='block4_pool')(x)
# Block 5
x = Conv2D(512, (3, 3), activation='relu', padding='same', name='block5_conv1')(x)
x = Conv2D(512, (3, 3), activation='relu', padding='same', name='block5_conv2')(x)
x = Conv2D(512, (3, 3), activation='relu', padding='same', name='block5_conv3')(x)
# x = MaxPooling2D((2, 2), strides=(2, 2), name='block5_pool')(x)
return x
def fmeasure(y_true, y_pred):
"""
Calculate F1 score for given numpy arrays or keras tensors
Args:
y_true: true labels
y_pred: predicted labels
Returns:
F1 score
"""
try:
_ = K.is_keras_tensor(y_pred)
return fbeta_score_K(y_true, y_pred, beta=1)
except ValueError:
return fbeta_score_np(y_true, y_pred, beta=1)
def nn_base(input_tensor=None, trainable=False):
# Determine proper input shape
if K.image_dim_ordering() == 'th':
input_shape = (3, None, None)
else:
input_shape = (None, None, 3)
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
if not K.is_keras_tensor(input_tensor):
img_input = Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
if K.image_dim_ordering() == 'tf':
bn_axis = 3
else:
bn_axis = 1
x = ZeroPadding2D((3, 3))(img_input)
x = Convolution2D(64, (7, 7), strides=(2, 2), name='conv1', trainable = trainable)(x)
x = FixedBatchNormalization(axis=bn_axis, name='bn_conv1')(x)
x = Activation('relu')(x)
x = MaxPooling2D((3, 3), strides=(2, 2))(x)
x = conv_block(x, 3, [64, 64, 256], stage=2, block='a', strides=(1, 1), trainable = trainable)
x = identity_block(x, 3, [64, 64, 256], stage=2, block='b', trainable = trainable)
x = identity_block(x, 3, [64, 64, 256], stage=2, block='c', trainable = trainable)
x = conv_block(x, 3, [128, 128, 512], stage=3, block='a', trainable = trainable)
x = identity_block(x, 3, [128, 128, 512], stage=3, block='b', trainable = trainable)
x = identity_block(x, 3, [128, 128, 512], stage=3, block='c', trainable = trainable)
x = identity_block(x, 3, [128, 128, 512], stage=3, block='d', trainable = trainable)
x = conv_block(x, 3, [256, 256, 1024], stage=4, block='a', trainable = trainable)
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='b', trainable = trainable)
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='c', trainable = trainable)
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='d', trainable = trainable)
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='e', trainable = trainable)
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='f', trainable = trainable)
return x
def MusicTaggerCRNN(weights='msd', input_tensor=None,
include_top=True):
'''Instantiate the MusicTaggerCRNN architecture,
optionally loading weights pre-trained
on Million Song Dataset. Note that when using TensorFlow,
for best performance you should set
`image_dim_ordering="tf"` in your Keras config
at ~/.keras/keras.json.
The model and the weights are compatible with both
TensorFlow and Theano. The dimension ordering
convention used by the model is the one
specified in your Keras config file.
For preparing mel-spectrogram input, see
`audio_conv_utils.py` in [applications](https://github.com/fchollet/keras/tree/master/keras/applications).
You will need to install [Librosa](http://librosa.github.io/librosa/)
to use it.
# Arguments
weights: one of `None` (random initialization)
or "msd" (pre-training on ImageNet).
input_tensor: optional Keras tensor (i.e. output of `layers.Input()`)
to use as image input for the model.
include_top: whether to include the 1 fully-connected
layer (output layer) at the top of the network.
If False, the network outputs 32-dim features.
# Returns
A Keras model instance.
'''
if weights not in {'msd', None}:
raise ValueError('The `weights` argument should be either '
'`None` (random initialization) or `msd` '
'(pre-training on Million Song Dataset).')
# Determine proper input shape
if K.image_dim_ordering() == 'th':
input_shape = (1, 96, 1366)
else:
input_shape = (96, 1366, 1)
if input_tensor is None:
melgram_input = Input(shape=input_shape)
else:
if not K.is_keras_tensor(input_tensor):
melgram_input = Input(tensor=input_tensor, shape=input_shape)
else:
melgram_input = input_tensor
# Determine input axis
if K.image_dim_ordering() == 'th':
channel_axis = 1
freq_axis = 2
time_axis = 3
else:
channel_axis = 3
freq_axis = 1
time_axis = 2
# Input block
x = ZeroPadding2D(padding=(0, 37))(melgram_input)
x = BatchNormalization(axis=time_axis, name='bn_0_freq')(x)
# Conv block 1
x = Convolution2D(64, 3, 3, border_mode='same', name='conv1')(x)
x = BatchNormalization(axis=channel_axis, mode=0, name='bn1')(x)
x = ELU()(x)
x = MaxPooling2D(pool_size=(2, 2), strides=(2, 2), name='pool1')(x)
# Conv block 2
x = Convolution2D(128, 3, 3, border_mode='same', name='conv2')(x)
x = BatchNormalization(axis=channel_axis, mode=0, name='bn2')(x)
x = ELU()(x)
x = MaxPooling2D(pool_size=(3, 3), strides=(3, 3), name='pool2')(x)
# Conv block 3
x = Convolution2D(128, 3, 3, border_mode='same', name='conv3')(x)
x = BatchNormalization(axis=channel_axis, mode=0, name='bn3')(x)
x = ELU()(x)
x = MaxPooling2D(pool_size=(4, 4), strides=(4, 4), name='pool3')(x)
# Conv block 4
x = Convolution2D(128, 3, 3, border_mode='same', name='conv4')(x)
x = BatchNormalization(axis=channel_axis, mode=0, name='bn4')(x)
x = ELU()(x)
x = MaxPooling2D(pool_size=(4, 4), strides=(4, 4), name='pool4')(x)
# reshaping
if K.image_dim_ordering() == 'th':
x = Permute((3, 1, 2))(x)
x = Reshape((15, 128))(x)
# GRU block 1, 2, output
x = GRU(32, return_sequences=True, name='gru1')(x)
x = GRU(32, return_sequences=False, name='gru2')(x)
if include_top:
x = Dense(50, activation='sigmoid', name='output')(x)
# Create model
model = Model(melgram_input, x)
if weights is None:
return model
else:
# Load weights
if K.image_dim_ordering() == 'tf':
weights_path = get_file('music_tagger_crnn_weights_tf_kernels_tf_dim_ordering.h5',
TF_WEIGHTS_PATH,
cache_subdir='models')
else:
weights_path = get_file('music_tagger_crnn_weights_tf_kernels_th_dim_ordering.h5',
TH_WEIGHTS_PATH,
cache_subdir='models')
model.load_weights(weights_path, by_name=True)
if K.backend() == 'theano':
convert_all_kernels_in_model(model)
return model
def VGG16(include_top=True, weights='imagenet',
input_tensor=None, input_shape=None):
if weights not in {'imagenet', None}:
raise ValueError('The `weights` argument should be either '
'`None` (random initialization) or `imagenet` '
'(pre-training on ImageNet).')
# Determine proper input shape
input_shape = _obtain_input_shape(input_shape,
default_size=224,
min_size=48,
dim_ordering=K.image_dim_ordering(),
include_top=include_top)
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
if not K.is_keras_tensor(input_tensor):
img_input = Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
# Block 1
x = Convolution2D(64, 3, 3, activation='relu', border_mode='same', name='block1_conv1')(img_input)
x = Convolution2D(64, 3, 3, activation='relu', border_mode='same', name='block1_conv2')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='block1_pool')(x)
# Block 2
x = Convolution2D(128, 3, 3, activation='relu', border_mode='same', name='block2_conv1')(x)
x = Convolution2D(128, 3, 3, activation='relu', border_mode='same', name='block2_conv2')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='block2_pool')(x)
# Block 3
x = Convolution2D(256, 3, 3, activation='relu', border_mode='same', name='block3_conv1')(x)
x = Convolution2D(256, 3, 3, activation='relu', border_mode='same', name='block3_conv2')(x)
x = Convolution2D(256, 3, 3, activation='relu', border_mode='same', name='block3_conv3')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='block3_pool')(x)
# Block 4
x = Convolution2D(512, 3, 3, activation='relu', border_mode='same', name='block4_conv1')(x)
x = Convolution2D(512, 3, 3, activation='relu', border_mode='same', name='block4_conv2')(x)
x = Convolution2D(512, 3, 3, activation='relu', border_mode='same', name='block4_conv3')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='block4_pool')(x)
# Block 5
x = Convolution2D(512, 3, 3, activation='relu', border_mode='same', name='block5_conv1')(x)
x = Convolution2D(512, 3, 3, activation='relu', border_mode='same', name='block5_conv2')(x)
x = Convolution2D(512, 3, 3, activation='relu', border_mode='same', name='block5_conv3')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='block5_pool')(x)
if include_top:
# Classification block
x = Flatten(name='flatten')(x)
x = Dense(4096, activation='relu', name='fc1')(x)
x = Dropout(0.5)(x)
x = Dense(4096, activation='relu', name='fc2')(x)
x = Dropout(0.5)(x)
x = Dense(1000, activation='softmax', name='predictions')(x)
# Ensure that the model takes into account
# any potential predecessors of `input_tensor`.
if input_tensor is not None:
inputs = get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model.
model = Model(inputs, x, name='vgg16')
# load weights
if weights == 'imagenet':
if K.image_dim_ordering() == 'tf':
wname = TF_WEIGHTS if include_top else TF_WEIGHTS_NO_TOP
weights_path = get_file(wname, PATH+wname, cache_subdir='models')
model.load_weights(weights_path)
return model
def DenseNetFCN(input_shape, nb_dense_block=5, growth_rate=16, nb_layers_per_block=4,
reduction=0.0, dropout_rate=0.2, weight_decay=1E-4, init_conv_filters=48,
include_top=True, weights=None, input_tensor=None, classes=1, activation='sigmoid',
upsampling_conv=128, upsampling_type='deconv', early_transition=False,
transition_pooling='max', initial_kernel_size=(3, 3)):
'''Instantiate the DenseNet FCN architecture.
Note that when using TensorFlow,
for best performance you should set
`image_data_format='channels_last'` in your Keras config
at ~/.keras/keras.json.
# Arguments
nb_dense_block: number of dense blocks to add to end (generally = 3)
growth_rate: number of filters to add per dense block
nb_layers_per_block: number of layers in each dense block.
Can be a positive integer or a list.
If positive integer, a set number of layers per dense block.
If list, nb_layer is used as provided. Note that list size must
be (nb_dense_block + 1)
reduction: reduction factor of transition blocks.
Note : reduction value is inverted to compute compression.
dropout_rate: dropout rate
weight_decay: weight decay factor
init_conv_filters: number of layers in the initial convolution layer
include_top: whether to include the fully-connected
layer at the top of the network.
weights: one of `None` (random initialization) or
'cifar10' (pre-training on CIFAR-10)..
input_tensor: optional Keras tensor (i.e. output of `layers.Input()`)
to use as image input for the model.
input_shape: optional shape tuple, only to be specified
if `include_top` is False (otherwise the input shape
has to be `(32, 32, 3)` (with `channels_last` dim ordering)
or `(3, 32, 32)` (with `channels_first` dim ordering).
It should have exactly 3 inputs channels,
and width and height should be no smaller than 8.
E.g. `(200, 200, 3)` would be one valid value.
classes: optional number of classes to classify images
into, only to be specified if `include_top` is True, and
if no `weights` argument is specified.
activation: Type of activation at the top layer. Can be one of 'softmax' or 'sigmoid'.
Note that if sigmoid is used, classes must be 1.
upsampling_conv: number of convolutional layers in upsampling via subpixel convolution
upsampling_type: Can be one of 'deconv', 'upsampling' and
'subpixel'. Defines type of upsampling algorithm used.
batchsize: Fixed batch size. This is a temporary requirement for
computation of output shape in the case of Deconvolution2D layers.
Parameter will be removed in next iteration of Keras, which infers
output shape of deconvolution layers automatically.
early_transition: Start with an extra initial transition down and end with an extra
transition up to reduce the network size.
initial_kernel_size: The first Conv2D kernel might vary in size based on the
application, this parameter makes it configurable.
# Returns
A Keras model instance.
'''
if weights not in {None}:
raise ValueError('The `weights` argument should be '
'`None` (random initialization) as no '
'model weights are provided.')
upsampling_type = upsampling_type.lower()
if upsampling_type not in ['upsampling', 'deconv', 'subpixel']:
raise ValueError('Parameter "upsampling_type" must be one of "upsampling", '
'"deconv" or "subpixel".')
if input_shape is None:
raise ValueError('For fully convolutional models, input shape must be supplied.')
if type(nb_layers_per_block) is not list and nb_dense_block < 1:
raise ValueError('Number of dense layers per block must be greater than 1. Argument '
'value was %d.' % (nb_layers_per_block))
if activation not in ['softmax', 'sigmoid']:
raise ValueError('activation must be one of "softmax" or "sigmoid"')
if activation == 'sigmoid' and classes != 1:
raise ValueError('sigmoid activation can only be used when classes = 1')
# Determine proper input shape
min_size = 2 ** nb_dense_block
if K.image_data_format() == 'channels_first':
if input_shape is not None:
if ((input_shape[1] is not None and input_shape[1] < min_size) or
(input_shape[2] is not None and input_shape[2] < min_size)):
raise ValueError('Input size must be at least ' +
str(min_size) + 'x' + str(min_size) + ', got '
'`input_shape=' + str(input_shape) + '`')
else:
input_shape = (classes, None, None)
else:
if input_shape is not None:
if ((input_shape[0] is not None and input_shape[0] < min_size) or
(input_shape[1] is not None and input_shape[1] < min_size)):
raise ValueError('Input size must be at least ' +
str(min_size) + 'x' + str(min_size) + ', got '
'`input_shape=' + str(input_shape) + '`')
else:
input_shape = (None, None, classes)
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
if not K.is_keras_tensor(input_tensor):
img_input = Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
x = __create_fcn_dense_net(classes, img_input, include_top, nb_dense_block, growth_rate,
reduction, dropout_rate, weight_decay,
nb_layers_per_block, upsampling_conv, upsampling_type,
init_conv_filters, input_shape, activation,
early_transition, transition_pooling, initial_kernel_size)
# Ensure that the model takes into account
# any potential predecessors of `input_tensor`.
if input_tensor is not None:
inputs = get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model.
model = Model(inputs, x, name='fcn-densenet')
return model
def VGG16(include_top=True, weights='vggface',
input_tensor=None, input_shape=None,
pooling=None,
classes=2622):
input_shape = _obtain_input_shape(input_shape,
default_size=224,
min_size=48,
data_format=K.image_data_format(),
require_flatten=include_top)
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
if not K.is_keras_tensor(input_tensor):
img_input = Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
# Block 1
x = Conv2D(64, (3, 3), activation='relu', padding='same', name='conv1_1')(
img_input)
x = Conv2D(64, (3, 3), activation='relu', padding='same', name='conv1_2')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='pool1')(x)
# Block 2
x = Conv2D(128, (3, 3), activation='relu', padding='same', name='conv2_1')(
x)
x = Conv2D(128, (3, 3), activation='relu', padding='same', name='conv2_2')(
x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='pool2')(x)
# Block 3
x = Conv2D(256, (3, 3), activation='relu', padding='same', name='conv3_1')(
x)
x = Conv2D(256, (3, 3), activation='relu', padding='same', name='conv3_2')(
x)
x = Conv2D(256, (3, 3), activation='relu', padding='same', name='conv3_3')(
x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='pool3')(x)
# Block 4
x = Conv2D(512, (3, 3), activation='relu', padding='same', name='conv4_1')(
x)
x = Conv2D(512, (3, 3), activation='relu', padding='same', name='conv4_2')(
x)
x = Conv2D(512, (3, 3), activation='relu', padding='same', name='conv4_3')(
x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='pool4')(x)
# Block 5
x = Conv2D(512, (3, 3), activation='relu', padding='same', name='conv5_1')(
x)
x = Conv2D(512, (3, 3), activation='relu', padding='same', name='conv5_2')(
x)
x = Conv2D(512, (3, 3), activation='relu', padding='same', name='conv5_3')(
x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='pool5')(x)
if include_top:
# Classification block
x = Flatten(name='flatten')(x)
x = Dense(4096, name='fc6')(x)
x = Activation('relu', name='fc6/relu')(x)
x = Dense(4096, name='fc7')(x)
x = Activation('relu', name='fc7/relu')(x)
x = Dense(classes, name='fc8')(x)
x = Activation('softmax', name='fc8/softmax')(x)
else:
if pooling == 'avg':
x = GlobalAveragePooling2D()(x)
elif pooling == 'max':
x = GlobalMaxPooling2D()(x)
# Ensure that the model takes into account
# any potential predecessors of `input_tensor`.
if input_tensor is not None:
inputs = get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model.
model = Model(inputs, x, name='vggface_vgg16') # load weights
if weights == 'vggface':
if include_top:
weights_path = get_file('rcmalli_vggface_tf_vgg16.h5',
utils.
VGG16_WEIGHTS_PATH,
cache_subdir=utils.VGGFACE_DIR)
else:
weights_path = get_file('rcmalli_vggface_tf_notop_vgg16.h5',
utils.VGG16_WEIGHTS_PATH_NO_TOP,
cache_subdir=utils.VGGFACE_DIR)
model.load_weights(weights_path, by_name=True)
if K.backend() == 'theano':
layer_utils.convert_all_kernels_in_model(model)
if K.image_data_format() == 'channels_first':
if include_top:
maxpool = model.get_layer(name='pool5')
shape = maxpool.output_shape[1:]
dense = model.get_layer(name='fc6')
layer_utils.convert_dense_weights_data_format(dense, shape,
'channels_first')
if K.backend() == 'tensorflow':
warnings.warn('You are using the TensorFlow backend, yet you '
'are using the Theano '
'image data format convention '
'(`image_data_format="channels_first"`). '
'For best performance, set '
'`image_data_format="channels_last"` in '
'your Keras config '
'at ~/.keras/keras.json.')
return model
def fmeasure(y_true, y_pred):
try:
_ = K.is_keras_tensor(y_pred)
return fbeta_score_K(y_true, y_pred, beta=1)
except ValueError:
return fbeta_score_np(y_true, y_pred, beta=1)
def VGG19(include_top=True, weights='imagenet',
input_tensor=None):
'''Instantiate the VGG19 architecture,
optionally loading weights pre-trained
on ImageNet. Note that when using TensorFlow,
for best performance you should set
`image_dim_ordering="tf"` in your Keras config
at ~/.keras/keras.json.
The model and the weights are compatible with both
TensorFlow and Theano. The dimension ordering
convention used by the model is the one
specified in your Keras config file.
# Arguments
include_top: whether to include the 3 fully-connected
layers at the top of the network.
weights: one of `None` (random initialization)
or "imagenet" (pre-training on ImageNet).
input_tensor: optional Keras tensor (i.e. output of `layers.Input()`)
to use as image input for the model.
# Returns
A Keras model instance.
'''
if weights not in {'imagenet', None}:
raise ValueError('The `weights` argument should be either '
'`None` (random initialization) or `imagenet` '
'(pre-training on ImageNet).')
# Determine proper input shape
if K.image_dim_ordering() == 'th':
if include_top:
input_shape = (3, 224, 224)
else:
input_shape = (3, None, None)
else:
if include_top:
input_shape = (224, 224, 3)
else:
input_shape = (None, None, 3)
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
if not K.is_keras_tensor(input_tensor):
img_input = Input(tensor=input_tensor)
else:
img_input = input_tensor
# Block 1
x = Convolution2D(64, 3, 3, activation='relu', border_mode='same', name='block1_conv1')(img_input)
x = Convolution2D(64, 3, 3, activation='relu', border_mode='same', name='block1_conv2')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='block1_pool')(x)
# Block 2
x = Convolution2D(128, 3, 3, activation='relu', border_mode='same', name='block2_conv1')(x)
x = Convolution2D(128, 3, 3, activation='relu', border_mode='same', name='block2_conv2')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='block2_pool')(x)
# Block 3
x = Convolution2D(256, 3, 3, activation='relu', border_mode='same', name='block3_conv1')(x)
x = Convolution2D(256, 3, 3, activation='relu', border_mode='same', name='block3_conv2')(x)
x = Convolution2D(256, 3, 3, activation='relu', border_mode='same', name='block3_conv3')(x)
x = Convolution2D(256, 3, 3, activation='relu', border_mode='same', name='block3_conv4')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='block3_pool')(x)
# Block 4
x = Convolution2D(512, 3, 3, activation='relu', border_mode='same', name='block4_conv1')(x)
x = Convolution2D(512, 3, 3, activation='relu', border_mode='same', name='block4_conv2')(x)
x = Convolution2D(512, 3, 3, activation='relu', border_mode='same', name='block4_conv3')(x)
x = Convolution2D(512, 3, 3, activation='relu', border_mode='same', name='block4_conv4')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='block4_pool')(x)
# Block 5
x = Convolution2D(512, 3, 3, activation='relu', border_mode='same', name='block5_conv1')(x)
x = Convolution2D(512, 3, 3, activation='relu', border_mode='same', name='block5_conv2')(x)
x = Convolution2D(512, 3, 3, activation='relu', border_mode='same', name='block5_conv3')(x)
x = Convolution2D(512, 3, 3, activation='relu', border_mode='same', name='block5_conv4')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='block5_pool')(x)
if include_top:
# Classification block
x = Flatten(name='flatten')(x)
x = Dense(4096, activation='relu', name='fc1')(x)
x = Dense(4096, activation='relu', name='fc2')(x)
x = Dense(1000, activation='softmax', name='predictions')(x)
# Create model
model = Model(img_input, x)
# load weights
if weights == 'imagenet':
print('K.image_dim_ordering:', K.image_dim_ordering())
if K.image_dim_ordering() == 'th':
if include_top:
weights_path = get_file('vgg19_weights_th_dim_ordering_th_kernels.h5',
TH_WEIGHTS_PATH,
cache_subdir='models')
else:
weights_path = get_file('vgg19_weights_th_dim_ordering_th_kernels_notop.h5',
TH_WEIGHTS_PATH_NO_TOP,
cache_subdir='models')
model.load_weights(weights_path)
if K.backend() == 'tensorflow':
warnings.warn('You are using the TensorFlow backend, yet you '
'are using the Theano '
'image dimension ordering convention '
'(`image_dim_ordering="th"`). '
'For best performance, set '
'`image_dim_ordering="tf"` in '
'your Keras config '
'at ~/.keras/keras.json.')
convert_all_kernels_in_model(model)
else:
if include_top:
weights_path = get_file('vgg19_weights_tf_dim_ordering_tf_kernels.h5',
TF_WEIGHTS_PATH,
cache_subdir='models')
else:
weights_path = get_file('vgg19_weights_tf_dim_ordering_tf_kernels_notop.h5',
TF_WEIGHTS_PATH_NO_TOP,
cache_subdir='models')
model.load_weights(weights_path)
if K.backend() == 'theano':
convert_all_kernels_in_model(model)
return model
def SqueezeNet(input_tensor=None, input_shape=None,
weights='imagenet',
classes=1000):
if weights not in {'imagenet', None}:
raise ValueError('The `weights` argument should be either '
'`None` (random initialization) or `imagenet` '
'(pre-training on ImageNet).')
if weights == 'imagenet' and classes != 1000:
raise ValueError('If using `weights` as imagenet with `include_top`'
' as true, `classes` should be 1000')
input_shape = _obtain_input_shape(input_shape,
default_size=227,
min_size=48,
data_format=K.image_data_format(),
include_top=True)
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
if not K.is_keras_tensor(input_tensor):
img_input = Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
x = Convolution2D(64, (3, 3), strides=(2, 2), padding='valid', name='conv1')(img_input)
x = Activation('relu', name='relu_conv1')(x)
x = MaxPooling2D(pool_size=(3, 3), strides=(2, 2), name='pool1')(x)
x = fire_module(x, fire_id=2, squeeze=16, expand=64)
x = fire_module(x, fire_id=3, squeeze=16, expand=64)
x = MaxPooling2D(pool_size=(3, 3), strides=(2, 2), name='pool3')(x)
x = fire_module(x, fire_id=4, squeeze=32, expand=128)
x = fire_module(x, fire_id=5, squeeze=32, expand=128)
x = MaxPooling2D(pool_size=(3, 3), strides=(2, 2), name='pool5')(x)
x = fire_module(x, fire_id=6, squeeze=48, expand=192)
x = fire_module(x, fire_id=7, squeeze=48, expand=192)
x = fire_module(x, fire_id=8, squeeze=64, expand=256)
x = fire_module(x, fire_id=9, squeeze=64, expand=256)
x = Dropout(0.5, name='drop9')(x)
x = Convolution2D(classes, (1, 1), padding='valid', name='conv10')(x)
x = Activation('relu', name='relu_conv10')(x)
x = GlobalAveragePooling2D()(x)
out = Activation('softmax', name='loss')(x)
# Ensure that the model takes into account
# any potential predecessors of `input_tensor`.
if input_tensor is not None:
inputs = get_source_inputs(input_tensor)
else:
inputs = img_input
model = Model(inputs, out, name='squeezenet')
# load weights
if weights == 'imagenet':
weights_path = get_file('squeezenet_weights_tf_dim_ordering_tf_kernels.h5',
WEIGHTS_PATH,
cache_subdir='models')
model.load_weights(weights_path)
if K.image_data_format() == 'channels_first':
if K.backend() == 'tensorflow':
warnings.warn('You are using the TensorFlow backend, yet you '
'are using the Theano '
'image data format convention '
'(`image_data_format="channels_first"`). '
'For best performance, set '
'`image_data_format="channels_last"` in '
'your Keras config '
'at ~/.keras/keras.json.')
return model
def ShuffleNet(include_top=True, input_tensor=None, scale_factor=1.0, pooling='max',
input_shape=(224,224,3), groups=1, load_model=None, num_shuffle_units=[3, 7, 3],
bottleneck_ratio=0.25, classes=1000):
"""
ShuffleNet implementation for Keras 2
ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices
Xiangyu Zhang, Xinyu Zhou, Mengxiao Lin, Jian Sun
https://arxiv.org/pdf/1707.01083.pdf
Note that only TensorFlow is supported for now, therefore it only works
with the data format `image_data_format='channels_last'` in your Keras
config at `~/.keras/keras.json`.
Parameters
----------
include_top: bool(True)
whether to include the fully-connected layer at the top of the network.
input_tensor:
optional Keras tensor (i.e. output of `layers.Input()`) to use as image input for the model.
scale_factor:
scales the number of output channels
input_shape:
pooling:
Optional pooling mode for feature extraction
when `include_top` is `False`.
- `None` means that the output of the model
will be the 4D tensor output of the
last convolutional layer.
- `avg` means that global average pooling
will be applied to the output of the
last convolutional layer, and thus
the output of the model will be a
2D tensor.
- `max` means that global max pooling will
be applied.
groups: int
number of groups per channel
num_shuffle_units: list([3,7,3])
number of stages (list length) and the number of shufflenet units in a
stage beginning with stage 2 because stage 1 is fixed
e.g. idx 0 contains 3 + 1 (first shuffle unit in each stage differs) shufflenet units for stage 2
idx 1 contains 7 + 1 Shufflenet Units for stage 3 and
idx 2 contains 3 + 1 Shufflenet Units
bottleneck_ratio:
bottleneck ratio implies the ratio of bottleneck channels to output channels.
For example, bottleneck ratio = 1 : 4 means the output feature map is 4 times
the width of the bottleneck feature map.
classes: int(1000)
number of classes to predict
Returns
-------
A Keras model instance
References
----------
- [ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices]
(http://www.arxiv.org/pdf/1707.01083.pdf)
"""
if K.backend() != 'tensorflow':
raise RuntimeError('Only TensorFlow backend is currently supported, '
'as other backends do not support ')
name = "ShuffleNet_%.2gX_g%d_br_%.2g_%s" % (scale_factor, groups, bottleneck_ratio, "".join([str(x) for x in num_shuffle_units]))
input_shape = _obtain_input_shape(input_shape,
default_size=224,
min_size=28,
require_flatten=include_top,
data_format=K.image_data_format())
out_dim_stage_two = {1: 144, 2: 200, 3: 240, 4: 272, 8: 384}
if groups not in out_dim_stage_two:
raise ValueError("Invalid number of groups.")
if pooling not in ['max','avg']:
raise ValueError("Invalid value for pooling.")
if not (float(scale_factor) * 4).is_integer():
raise ValueError("Invalid value for scale_factor. Should be x over 4.")
exp = np.insert(np.arange(0, len(num_shuffle_units), dtype=np.float32), 0, 0)
out_channels_in_stage = 2 ** exp
out_channels_in_stage *= out_dim_stage_two[groups] # calculate output channels for each stage
out_channels_in_stage[0] = 24 # first stage has always 24 output channels
out_channels_in_stage *= scale_factor
out_channels_in_stage = out_channels_in_stage.astype(int)
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
if not K.is_keras_tensor(input_tensor):
img_input = Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
# create shufflenet architecture
x = Conv2D(filters=out_channels_in_stage[0], kernel_size=(3, 3), padding='same',
use_bias=False, strides=(2, 2), activation="relu", name="conv1")(img_input)
x = MaxPooling2D(pool_size=(3, 3), strides=(2, 2), padding='same', name="maxpool1")(x)
# create stages containing shufflenet units beginning at stage 2
for stage in range(0, len(num_shuffle_units)):
repeat = num_shuffle_units[stage]
x = _block(x, out_channels_in_stage, repeat=repeat,
bottleneck_ratio=bottleneck_ratio,
groups=groups, stage=stage + 2)
if pooling == 'avg':
x = GlobalAveragePooling2D(name="global_pool")(x)
elif pooling == 'max':
x = GlobalMaxPooling2D(name="global_pool")(x)
if include_top:
x = Dense(units=classes, name="fc")(x)
x = Activation('softmax', name='softmax')(x)
if input_tensor is not None:
inputs = get_source_inputs(input_tensor)
else:
inputs = img_input
model = Model(inputs=inputs, outputs=x, name=name)
if load_model is not None:
model.load_weights('', by_name=True)
return model
def ResNet50(include_top=True, weights='imagenet',
input_tensor=None, input_shape=None,
pooling=None,
classes=1000):
"""Instantiates the ResNet50 architecture.
Optionally loads weights pre-trained
on ImageNet. Note that when using TensorFlow,
for best performance you should set
`image_data_format="channels_last"` in your Keras config
at ~/.keras/keras.json.
The model and the weights are compatible with both
TensorFlow and Theano. The data format
convention used by the model is the one
specified in your Keras config file.
# Arguments
include_top: whether to include the fully-connected
layer at the top of the network.
weights: one of `None` (random initialization)
or "imagenet" (pre-training on ImageNet).
input_tensor: optional Keras tensor (i.e. output of `layers.Input()`)
to use as image input for the model.
input_shape: optional shape tuple, only to be specified
if `include_top` is False (otherwise the input shape
has to be `(224, 224, 3)` (with `channels_last` data format)
or `(3, 224, 244)` (with `channels_first` data format).
It should have exactly 3 inputs channels,
and width and height should be no smaller than 197.
E.g. `(200, 200, 3)` would be one valid value.
pooling: Optional pooling mode for feature extraction
when `include_top` is `False`.
- `None` means that the output of the model will be
the 4D tensor output of the
last convolutional layer.
- `avg` means that global average pooling
will be applied to the output of the
last convolutional layer, and thus
the output of the model will be a 2D tensor.
- `max` means that global max pooling will
be applied.
classes: optional number of classes to classify images
into, only to be specified if `include_top` is True, and
if no `weights` argument is specified.
# Returns
A Keras model instance.
# Raises
ValueError: in case of invalid argument for `weights`,
or invalid input shape.
"""
if weights not in {'imagenet', None}:
raise ValueError('The `weights` argument should be either '
'`None` (random initialization) or `imagenet` '
'(pre-training on ImageNet).')
if weights == 'imagenet' and include_top and classes != 1000:
raise ValueError('If using `weights` as imagenet with `include_top`'
' as true, `classes` should be 1000')
# Determine proper input shape
input_shape = _obtain_input_shape(input_shape,
default_size=224,
min_size=197,
data_format=K.image_data_format(),
# include_top=include_top)
require_flatten=include_top)
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
if not K.is_keras_tensor(input_tensor):
img_input = Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
if K.image_data_format() == 'channels_last':
bn_axis = 3
else:
bn_axis = 1
x = ZeroPadding2D((3, 3))(img_input)
x = Conv2D(64, (7, 7), strides=(2, 2), name='conv1')(x)
x = BatchNormalization(axis=bn_axis, name='bn_conv1')(x)
x = Activation('relu')(x)
x = MaxPooling2D((3, 3), strides=(2, 2))(x)
x = conv_block(x, 3, [64, 64, 256], stage=2, block='a', strides=(1, 1))
x = identity_block(x, 3, [64, 64, 256], stage=2, block='b')
x = identity_block(x, 3, [64, 64, 256], stage=2, block='c')
x = conv_block(x, 3, [128, 128, 512], stage=3, block='a')
x = identity_block(x, 3, [128, 128, 512], stage=3, block='b')
x = identity_block(x, 3, [128, 128, 512], stage=3, block='c')
x = identity_block(x, 3, [128, 128, 512], stage=3, block='d')
x = conv_block(x, 3, [256, 256, 1024], stage=4, block='a')
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='b')
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='c')
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='d')
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='e')
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='f')
x = conv_block(x, 3, [512, 512, 2048], stage=5, block='a')
x = identity_block(x, 3, [512, 512, 2048], stage=5, block='b')
x = identity_block(x, 3, [512, 512, 2048], stage=5, block='c')
x = AveragePooling2D((7, 7), name='avg_pool')(x)
if include_top:
x = Flatten()(x)
x = Dense(classes, activation='softmax', name='fc1000')(x)
else:
if pooling == 'avg':
x = GlobalAveragePooling2D()(x)
elif pooling == 'max':
x = GlobalMaxPooling2D()(x)
# Ensure that the model takes into account
# any potential predecessors of `input_tensor`.
if input_tensor is not None:
inputs = get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model.
model = Model(inputs, x, name='resnet50')
# load weights
if weights == 'imagenet':
if include_top:
weights_path = get_file('resnet50_weights_tf_dim_ordering_tf_kernels.h5',
WEIGHTS_PATH,
cache_subdir='models',
md5_hash='a7b3fe01876f51b976af0dea6bc144eb')
else:
weights_path = get_file('resnet50_weights_tf_dim_ordering_tf_kernels_notop.h5',
WEIGHTS_PATH_NO_TOP,
cache_subdir='models',
md5_hash='a268eb855778b3df3c7506639542a6af')
model.load_weights(weights_path)
if K.backend() == 'theano':
layer_utils.convert_all_kernels_in_model(model)
if K.image_data_format() == 'channels_first':
if include_top:
maxpool = model.get_layer(name='avg_pool')
shape = maxpool.output_shape[1:]
dense = model.get_layer(name='fc1000')
layer_utils.convert_dense_weights_data_format(dense, shape, 'channels_first')
if K.backend() == 'tensorflow':
warnings.warn('You are using the TensorFlow backend, yet you '
'are using the Theano '
'image data format convention '
'(`image_data_format="channels_first"`). '
'For best performance, set '
'`image_data_format="channels_last"` in '
'your Keras config '
'at ~/.keras/keras.json.')
return model
def VGG19(include_top=True,
weights='imagenet',
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000):
"""Instantiates the VGG19 architecture.
Optionally loads weights pre-trained
on ImageNet. Note that when using TensorFlow,
for best performance you should set
`image_data_format="channels_last"` in your Keras config
at ~/.keras/keras.json.
The model and the weights are compatible with both
TensorFlow and Theano. The data format
convention used by the model is the one
specified in your Keras config file.
# Arguments
include_top: whether to include the 3 fully-connected
layers at the top of the network.
weights: one of `None` (random initialization)
or "imagenet" (pre-training on ImageNet).
input_tensor: optional Keras tensor (i.e. output of `layers.Input()`)
to use as image input for the model.
input_shape: optional shape tuple, only to be specified
if `include_top` is False (otherwise the input shape
has to be `(224, 224, 3)` (with `channels_last` data format)
or `(3, 224, 244)` (with `channels_first` data format).
It should have exactly 3 inputs channels,
and width and height should be no smaller than 48.
E.g. `(200, 200, 3)` would be one valid value.
pooling: Optional pooling mode for feature extraction
when `include_top` is `False`.
- `None` means that the output of the model will be
the 4D tensor output of the
last convolutional layer.
- `avg` means that global average pooling
will be applied to the output of the
last convolutional layer, and thus
the output of the model will be a 2D tensor.
- `max` means that global max pooling will
be applied.
classes: optional number of classes to classify images
into, only to be specified if `include_top` is True, and
if no `weights` argument is specified.
# Returns
A Keras model instance.
# Raises
ValueError: in case of invalid argument for `weights`,
or invalid input shape.
"""
if weights not in {'imagenet', None}:
raise ValueError('The `weights` argument should be either '
'`None` (random initialization) or `imagenet` '
'(pre-training on ImageNet).')
if weights == 'imagenet' and include_top and classes != 1000:
raise ValueError('If using `weights` as imagenet with `include_top`'
' as true, `classes` should be 1000')
# Determine proper input shape
input_shape = _obtain_input_shape(input_shape,
default_size=224,
min_size=48,
data_format=K.image_data_format(),
require_flatten=include_top)
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
if not K.is_keras_tensor(input_tensor):
img_input = Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
# Block 1
x = Conv2D(64, (3, 3),
activation='relu',
padding='same',
name='block1_conv1')(img_input)
x = Conv2D(64, (3, 3),
activation='relu',
padding='same',
name='block1_conv2')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='block1_pool')(x)
# Block 2
x = Conv2D(128, (3, 3),
activation='relu',
padding='same',
name='block2_conv1')(x)
x = Conv2D(128, (3, 3),
activation='relu',
padding='same',
name='block2_conv2')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='block2_pool')(x)
# Block 3
x = Conv2D(256, (3, 3),
activation='relu',
padding='same',
name='block3_conv1')(x)
x = Conv2D(256, (3, 3),
activation='relu',
padding='same',
name='block3_conv2')(x)
x = Conv2D(256, (3, 3),
activation='relu',
padding='same',
name='block3_conv3')(x)
x = Conv2D(256, (3, 3),
activation='relu',
padding='same',
name='block3_conv4')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='block3_pool')(x)
# Block 4
x = Conv2D(512, (3, 3),
activation='relu',
padding='same',
name='block4_conv1')(x)
x = Conv2D(512, (3, 3),
activation='relu',
padding='same',
name='block4_conv2')(x)
x = Conv2D(512, (3, 3),
activation='relu',
padding='same',
name='block4_conv3')(x)
x = Conv2D(512, (3, 3),
activation='relu',
padding='same',
name='block4_conv4')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='block4_pool')(x)
# Block 5
x = Conv2D(512, (3, 3),
activation='relu',
padding='same',
name='block5_conv1')(x)
x = Conv2D(512, (3, 3),
activation='relu',
padding='same',
name='block5_conv2')(x)
x = Conv2D(512, (3, 3),
activation='relu',
padding='same',
name='block5_conv3')(x)
x = Conv2D(512, (3, 3),
activation='relu',
padding='same',
name='block5_conv4')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='block5_pool')(x)
if include_top:
# Classification block
x = Flatten(name='flatten')(x)
x = Dense(4096, activation='relu', name='fc1')(x)
x = Dense(4096, activation='relu', name='fc2')(x)
x = Dense(classes, activation='softmax', name='predictions')(x)
else:
if pooling == 'avg':
x = GlobalAveragePooling2D()(x)
elif pooling == 'max':
x = GlobalMaxPooling2D()(x)
# Ensure that the model takes into account
# any potential predecessors of `input_tensor`.
if input_tensor is not None:
inputs = get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model.
model = Model(inputs, x, name='vgg19')
# load weights
if weights == 'imagenet':
if include_top:
weights_path = get_file(
'vgg19_weights_tf_dim_ordering_tf_kernels.h5',
WEIGHTS_PATH,
cache_subdir='models')
else:
weights_path = get_file(
'vgg19_weights_tf_dim_ordering_tf_kernels_notop.h5',
WEIGHTS_PATH_NO_TOP,
cache_subdir='models')
model.load_weights(weights_path)
if K.backend() == 'theano':
layer_utils.convert_all_kernels_in_model(model)
if K.image_data_format() == 'channels_first':
if include_top:
maxpool = model.get_layer(name='block5_pool')
shape = maxpool.output_shape[1:]
dense = model.get_layer(name='fc1')
layer_utils.convert_dense_weights_data_format(
dense, shape, 'channels_first')
if K.backend() == 'tensorflow':
warnings.warn('You are using the TensorFlow backend, yet you '
'are using the Theano '
'image data format convention '
'(`image_data_format="channels_first"`). '
'For best performance, set '
'`image_data_format="channels_last"` in '
'your Keras config '
'at ~/.keras/keras.json.')
return model
def ResNext(input_shape=None,
depth=29,
cardinality=8,
width=64,
weight_decay=5e-4,
include_top=True,
weights=None,
input_tensor=None,
pooling=None,
classes=10):
"""Instantiate the ResNeXt architecture. Note that ,
when using TensorFlow for best performance you should set
`image_data_format="channels_last"` in your Keras config
at ~/.keras/keras.json.
The model are compatible with both
TensorFlow and Theano. The dimension ordering
convention used by the model is the one
specified in your Keras config file.
# Arguments
depth: number or layers in the ResNeXt model. Can be an
integer or a list of integers.
cardinality: the size of the set of transformations
width: multiplier to the ResNeXt width (number of filters)
weight_decay: weight decay (l2 norm)
include_top: whether to include the fully-connected
layer at the top of the network.
weights: `None` (random initialization)
input_tensor: optional Keras tensor (i.e. output of `layers.Input()`)
to use as image input for the model.
input_shape: optional shape tuple, only to be specified
if `include_top` is False (otherwise the input shape
has to be `(32, 32, 3)` (with `tf` dim ordering)
or `(3, 32, 32)` (with `th` dim ordering).
It should have exactly 3 inputs channels,
and width and height should be no smaller than 8.
E.g. `(200, 200, 3)` would be one valid value.
pooling: Optional pooling mode for feature extraction
when `include_top` is `False`.
- `None` means that the output of the model will be
the 4D tensor output of the
last convolutional layer.
- `avg` means that global average pooling
will be applied to the output of the
last convolutional layer, and thus
the output of the model will be a 2D tensor.
- `max` means that global max pooling will
be applied.
classes: optional number of classes to classify images
into, only to be specified if `include_top` is True, and
if no `weights` argument is specified.
# Returns
A Keras model instance.
"""
if weights not in {'cifar10', None}:
raise ValueError('The `weights` argument should be either '
'`None` (random initialization) or `cifar10` '
'(pre-training on CIFAR-10).')
if weights == 'cifar10' and include_top and classes != 10:
raise ValueError('If using `weights` as CIFAR 10 with `include_top`'
' as true, `classes` should be 10')
if type(depth) == int:
if (depth - 2) % 9 != 0:
raise ValueError(
'Depth of the network must be such that (depth - 2)'
'should be divisible by 9.')
# Determine proper input shape
input_shape = _obtain_input_shape(input_shape,
default_size=32,
min_size=8,
data_format=K.image_data_format(),
require_flatten=include_top)
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
if not K.is_keras_tensor(input_tensor):
img_input = Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
x = __create_res_next(classes, img_input, include_top, depth, cardinality,
width, weight_decay, pooling)
# Ensure that the model takes into account
# any potential predecessors of `input_tensor`.
if input_tensor is not None:
inputs = get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model.
model = Model(inputs, x, name='resnext')
# load weights
if weights == 'cifar10':
if (depth == 29) and (cardinality == 8) and (width == 64):
# Default parameters match. Weights for this model exist:
if K.image_data_format() == 'channels_first':
if include_top:
weights_path = get_file(
'resnext_cifar_10_8_64_th_dim_ordering_th_kernels.h5',
CIFAR_TH_WEIGHTS_PATH,
cache_subdir='models')
else:
weights_path = get_file(
'resnext_cifar_10_8_64_th_dim_ordering_th_kernels_no_top.h5',
CIFAR_TH_WEIGHTS_PATH_NO_TOP,
cache_subdir='models')
model.load_weights(weights_path)
if K.backend() == 'tensorflow':
warnings.warn(
'You are using the TensorFlow backend, yet you '
'are using the Theano '
'image dimension ordering convention '
'(`image_dim_ordering="th"`). '
'For best performance, set '
'`image_dim_ordering="tf"` in '
'your Keras config '
'at ~/.keras/keras.json.')
convert_all_kernels_in_model(model)
else:
if include_top:
weights_path = get_file(
'resnext_cifar_10_8_64_tf_dim_ordering_tf_kernels.h5',
CIFAR_TF_WEIGHTS_PATH,
cache_subdir='models')
else:
weights_path = get_file(
'resnext_cifar_10_8_64_tf_dim_ordering_tf_kernels_no_top.h5',
CIFAR_TF_WEIGHTS_PATH_NO_TOP,
cache_subdir='models')
model.load_weights(weights_path)
if K.backend() == 'theano':
convert_all_kernels_in_model(model)
return model
def build_heatmap_inference(in_tensor, config, names = None):
num_detections = config.DETECTION_MAX_INSTANCES
img_h, img_w = config.IMAGE_SHAPE[:2]
batch_size = config.BATCH_SIZE
num_classes = config.NUM_CLASSES
heatmap_scale = config.HEATMAP_SCALE_FACTOR
grid_h, grid_w = config.IMAGE_SHAPE[:2] // heatmap_scale
# rois_per_image = (in_tensor.shape)[2] # same as below:
rois_per_image = config.DETECTION_PER_CLASS
print('\n ')
print(' > build_heatmap_inference() : ', names )
print(' orignal in_tensor shape : ', in_tensor.shape)
# rois per image is determined by size of input tensor
# detection mode: config.TRAIN_ROIS_PER_IMAGE
# ground_truth : config.DETECTION_MAX_INSTANCES
# strt_cls = 0 if rois_per_image == 32 else 1
print(' num of bboxes per class is : ', rois_per_image )
#-----------------------------------------------------------------------------
## Stack non_zero bboxes from in_tensor into pt2_dense
#-----------------------------------------------------------------------------
# pt2_ind shape is [?, 3].
# pt2_ind[0] corresponds to image_index
# pt2_ind[1] corresponds to class_index
# pt2_ind[2] corresponds to roi row_index
# pt2_dense shape is [?, 6]
# pt2_dense[0] is image index
# pt2_dense[1:4] roi cooridnaytes
# pt2_dense[5] is class id
#
#
#-----------------------------------------------------------------------------
pt2_sum = tf.reduce_sum(tf.abs(in_tensor[:,:,:,:4]), axis=-1)
pt2_ind = tf.where(pt2_sum > 0)
pt2_dense = tf.gather_nd( in_tensor, pt2_ind)
print(' pt2_sum shape : ', pt2_sum.shape)
print(' pt2_ind shape : ', pt2_ind.shape)
print(' pt2_dense shape: ', pt2_dense.get_shape())
##-----------------------------------------------------------------------------
## Build mesh-grid to hold pixel coordinates
##-----------------------------------------------------------------------------
X = tf.range(grid_w, dtype=tf.int32)
Y = tf.range(grid_h, dtype=tf.int32)
X, Y = tf.meshgrid(X, Y)
# duplicate (repeat) X and Y into a batch_size x rois_per_image tensor
print(' X/Y shapes :', X.get_shape(), Y.get_shape())
ones = tf.ones([tf.shape(pt2_dense)[0] , 1, 1], dtype = tf.int32)
rep_X = ones * X
rep_Y = ones * Y
print(' Ones: ', ones.shape)
print(' ones_exp * X', ones.shape, '*', X.shape, '= ',rep_X.shape)
print(' ones_exp * Y', ones.shape, '*', Y.shape, '= ',rep_Y.shape)
# # stack the X and Y grids
pos_grid = tf.to_float(tf.stack([rep_X,rep_Y], axis = -1))
print(' pos_grid before transpse : ', pos_grid.get_shape())
pos_grid = tf.transpose(pos_grid,[1,2,0,3])
print(' pos_grid after transpose : ', pos_grid.get_shape())
##-----------------------------------------------------------------------------
## Build mean and convariance tensors for Multivariate Normal Distribution
##-----------------------------------------------------------------------------
pt2_dense_scaled = pt2_dense[:,:4]/heatmap_scale
width = pt2_dense_scaled[:,3] - pt2_dense_scaled[:,1] # x2 - x1
height = pt2_dense_scaled[:,2] - pt2_dense_scaled[:,0]
cx = pt2_dense_scaled[:,1] + ( width / 2.0)
cy = pt2_dense_scaled[:,0] + ( height / 2.0)
means = tf.stack((cx,cy),axis = -1)
covar = tf.stack((width * 0.5 , height * 0.5), axis = -1)
covar = tf.sqrt(covar)
##-----------------------------------------------------------------------------
## Compute Normal Distribution for bounding boxes
##-----------------------------------------------------------------------------
tfd = tf.contrib.distributions
mvn = tfd.MultivariateNormalDiag(loc = means, scale_diag = covar)
prob_grid = mvn.prob(pos_grid)
print(' >> input to MVN.PROB: pos_grid (meshgrid) shape: ', pos_grid.shape)
print(' Prob_grid shape from mvn.probe: ',prob_grid.shape)
prob_grid = tf.transpose(prob_grid,[2,0,1])
print(' Prob_grid shape after tanspose: ',prob_grid.shape)
print(' << output probabilities shape : ' , prob_grid.shape)
#-------------------------------------------------------------------------------------
# Kill distributions of NaN boxes (resulting from bboxes with height/width of zero
# which cause singular sigma cov matrices
#-------------------------------------------------------------------------------------
# prob_grid = tf.where(tf.is_nan(prob_grid), tf.zeros_like(prob_grid), prob_grid)
##---------------------------------------------------------------------------------------------
## (1) apply normalization per bbox heatmap instance
##---------------------------------------------------------------------------------------------
print('\n normalization ------------------------------------------------------')
normalizer = tf.reduce_max(prob_grid, axis=[-2,-1], keepdims = True)
normalizer = tf.where(normalizer < 1.0e-15, tf.ones_like(normalizer), normalizer)
print(' normalizer : ', normalizer.shape)
prob_grid_norm = prob_grid / normalizer
##---------------------------------------------------------------------------------------------
## (2) multiply normalized heatmap by normalized score in in_tensor/ (pt2_dense column 7)
## broadcasting : https://stackoverflow.com/questions/49705831/automatic-broadcasting-in-tensorflow
##---------------------------------------------------------------------------------------------
# Using the double tf.transpose, we dont need this any more
# scr = tf.expand_dims(tf.expand_dims(pt2_dense[:,7],axis = -1), axis =-1)
prob_grid_norm_scaled = tf.transpose(tf.transpose(prob_grid_norm) * pt2_dense[:,7])
print(' prob_grid_norm_scaled : ', prob_grid_norm_scaled.shape)
# maxes2 = tf.reduce_max(prob_grid_norm_scaled, axis=[-2,-1], keepdims = True)
# print(' shape of maxes2 : ', maxes2.shape)
##-------------------------------------------------------------------------------------
## (3) scatter out the probability distributions based on class
##-------------------------------------------------------------------------------------
print('\n Scatter out the probability distributions based on class --------------')
gauss_scatt = tf.scatter_nd(pt2_ind, prob_grid_norm_scaled,
[batch_size, num_classes, rois_per_image, grid_w, grid_h],
name = 'gauss_scatter')
print(' pt2_ind shape : ', pt2_ind.shape)
print(' prob_grid shape : ', prob_grid.shape)
print(' gauss_scatt : ', gauss_scatt.shape) # batch_sz , num_classes, num_rois, image_h, image_w
##-------------------------------------------------------------------------------------
## (4) SUM : Reduce and sum up gauss_scattered by class
##-------------------------------------------------------------------------------------
print('\n Reduce sum based on class ---------------------------------------------')
gauss_heatmap = tf.reduce_sum(gauss_scatt, axis=2, name='pred_heatmap2')
#--------------------------------------------------------------------------------------
# force small sums to zero - for now (09-11-18) commented out but could reintroduce based on test results
# gauss_heatmap = tf.where(gauss_heatmap < 1e-12, gauss_heatmap, tf.zeros_like(gauss_heatmap), name='Where1')
#--------------------------------------------------------------------------------------
print(' gaussian_heatmap : ', gauss_heatmap.get_shape(), 'Keras tensor ', KB.is_keras_tensor(gauss_heatmap) )
##---------------------------------------------------------------------------------------------
## (5) heatmap normalization
## normalizer is set to one when the max of class is zero
## this prevents elements of gauss_heatmap_norm computing to nan
##---------------------------------------------------------------------------------------------
print('\n normalization ------------------------------------------------------')
normalizer = tf.reduce_max(gauss_heatmap, axis=[-2,-1], keepdims = True)
normalizer = tf.where(normalizer < 1.0e-15, tf.ones_like(normalizer), normalizer)
gauss_heatmap_norm = gauss_heatmap / normalizer
print(' normalizer shape : ', normalizer.shape)
print(' gauss norm : ', gauss_heatmap_norm.shape ,' Keras tensor ', KB.is_keras_tensor(gauss_heatmap_norm) )
#-------------------------------------------------------------------------------------
# scatter out the probability distributions based on class
#-------------------------------------------------------------------------------------
# print('\n Scatter out the probability distributions based on class --------------')
# gauss_scatt = tf.scatter_nd(pt2_ind, prob_grid,
# [batch_size, num_classes, rois_per_image, grid_w, grid_h], name = 'gauss_scatter')
# print(' pt2_ind shape : ', pt2_ind.shape)
# print(' prob_grid shape : ', prob_grid.shape)
# print(' gauss_scatt : ', gauss_scatt.shape) # batch_sz , num_classes, num_rois, image_h, image_w
#-------------------------------------------------------------------------------------
# SUM : Reduce and sum up gauss_scattered by class
#-------------------------------------------------------------------------------------
# print('\n Reduce sum based on class ---------------------------------------------')
# gauss_heatmap = tf.reduce_sum(gauss_scatt, axis=2, name='pred_heatmap2')
# force small sums to zero - for now (09-11-18) commented out but could reintroduce based on test results
# gauss_heatmap = tf.where(gauss_heatmap < 1e-12, gauss_heatmap, tf.zeros_like(gauss_heatmap), name='Where1')
# print(' gaussian_hetmap : ', gauss_heatmap.get_shape(), 'Keras tensor ', KB.is_keras_tensor(gauss_heatmap))
#---------------------------------------------------------------------------------------------
# heatmap normalization per class
# normalizer is set to one when the max of class is zero
# this prevents elements of gauss_heatmap_norm computing to nan
#---------------------------------------------------------------------------------------------
# print('\n normalization ------------------------------------------------------')
# normalizer = tf.reduce_max(gauss_heatmap, axis=[-2,-1], keepdims = True)
# print(' normalizer shape : ', normalizer.shape)
# normalizer = tf.where(normalizer < 1.0e-15, tf.ones_like(normalizer), normalizer)
# gauss_heatmap_norm = gauss_heatmap / normalizer
# print(' gauss norm : ', gauss_heatmap_norm.shape ,' Keras tensor ', KB.is_keras_tensor(gauss_heatmap_norm) )
##--------------------------------------------------------------------------------------------
## Generate scores using prob_grid and pt2_dense - NEW METHOD
## added 09-21-2018
##--------------------------------------------------------------------------------------------
scores_from_sum2 = tf.map_fn(build_hm_score,
[prob_grid, pt2_dense_scaled, pt2_dense[:,7]],
dtype = tf.float32, swap_memory = True)
scores_scattered = tf.scatter_nd(pt2_ind, scores_from_sum2,
[batch_size, num_classes, rois_per_image, 3], name = 'scores_scattered')
gauss_scores = tf.concat([in_tensor, scores_scattered], axis = -1,name = names[0]+'_scores')
print(' scores_scattered shape : ', scores_scattered.shape)
print(' gauss_scores : ', gauss_scores.shape, ' Name: ', gauss_scores.name)
print(' gauss_scores (FINAL) : ', gauss_scores.shape, ' Keras tensor ', KB.is_keras_tensor(gauss_scores) )
##--------------------------------------------------------------------------------------------
## //create heatmap Append `in_tensor` and `scores_from_sum` to form `bbox_scores`
##--------------------------------------------------------------------------------------------
# gauss_heatmap = tf.transpose(gauss_heatmap,[0,2,3,1], name = names[0])
# print(' gauss_heatmap : ', gauss_heatmap.shape,' Keras tensor ', KB.is_keras_tensor(gauss_heatmap))
gauss_heatmap_norm = tf.transpose(gauss_heatmap_norm,[0,2,3,1], name = names[0]+'_norm')
print(' gauss_heatmap_norm : ', gauss_heatmap_norm.shape,' Keras tensor ', KB.is_keras_tensor(gauss_heatmap_norm) )
print(' complete')
return gauss_heatmap_norm, gauss_scores
def DenseNet(blocks,
include_top=True,
weights=None,
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000,
area1layers=0):
"""Instantiates the DenseNet architecture.
Optionally loads weights pre-trained
on ImageNet. Note that when using TensorFlow,
for best performance you should set
`image_data_format='channels_last'` in your Keras config
at ~/.keras/keras.json.
The model and the weights are compatible with
TensorFlow, Theano, and CNTK. The data format
convention used by the model is the one
specified in your Keras config file.
# Arguments
blocks: numbers of building blocks for the four dense layers.
include_top: whether to include the fully-connected
layer at the top of the network.
weights: one of `None` (random initialization),
'imagenet' (pre-training on ImageNet),
or the path to the weights file to be loaded.
input_tensor: optional Keras tensor (i.e. output of `layers.Input()`)
to use as image input for the model.
input_shape: optional shape tuple, only to be specified
if `include_top` is False (otherwise the input shape
has to be `(224, 224, 3)` (with `channels_last` data format)
or `(3, 224, 224)` (with `channels_first` data format).
It should have exactly 3 inputs channels.
pooling: optional pooling mode for feature extraction
when `include_top` is `False`.
- `None` means that the output of the model will be
the 4D tensor output of the
last convolutional layer.
- `avg` means that global average pooling
will be applied to the output of the
last convolutional layer, and thus
the output of the model will be a 2D tensor.
- `max` means that global max pooling will
be applied.
classes: optional number of classes to classify images
into, only to be specified if `include_top` is True, and
if no `weights` argument is specified.
# Returns
A Keras model instance.
# Raises
ValueError: in case of invalid argument for `weights`,
or invalid input shape.
"""
if not (weights in {'imagenet', None} or os.path.exists(weights)):
raise ValueError('The `weights` argument should be either '
'`None` (random initialization), `imagenet` '
'(pre-training on ImageNet), '
'or the path to the weights file to be loaded.')
if weights == 'imagenet' and include_top and classes != 1000:
raise ValueError('If using `weights` as imagenet with `include_top`'
' as true, `classes` should be 1000')
# Determine proper input shape
input_shape = _obtain_input_shape(input_shape,
default_size=224,
min_size=221,
data_format=K.image_data_format(),
require_flatten=include_top,
weights=weights)
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
if not K.is_keras_tensor(input_tensor):
img_input = Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
bn_axis = 3 if K.image_data_format() == 'channels_last' else 1
x = ZeroPadding2D(padding=((3, 3), (3, 3)))(img_input)
x = Conv2D(64, 7, strides=2, use_bias=False, name='conv1/conv')(x)
x = BatchNormalization(axis=bn_axis, epsilon=1.001e-5,
name='conv1/bn')(x)
x = Activation('relu', name='conv1/relu')(x)
x = ZeroPadding2D(padding=((1, 1), (1, 1)))(x)
x = MaxPooling2D(3, strides=2, name='pool1')(x)
x = dense_block(x, blocks[0], name='conv2')
x = transition_block(x, 0.5, name='pool2')
x = dense_block(x, blocks[1], name='conv3')
x = transition_block(x, 0.5, name='pool3')
x = dense_block(x, blocks[2], name='conv4')
x = transition_block(x, 0.5, name='pool4')
x = dense_block(x, blocks[3], name='conv5')
x = BatchNormalization(axis=bn_axis, epsilon=1.001e-5,
name='bn')(x)
if include_top:
x = GlobalAveragePooling2D(name='avg_pool')(x)
x = Dense(classes, activation='softmax', name='all_classes')(x)
else:
if pooling == 'avg':
x = GlobalAveragePooling2D(name='avg_pool')(x)
elif pooling == 'max':
x = GlobalMaxPooling2D(name='max_pool')(x)
# Ensure that the model takes into account
# any potential predecessors of `input_tensor`.
if input_tensor is not None:
inputs = get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model.
if blocks == [6, 12, 24, 16]:
model = Model(inputs, x, name='densenet121')
elif blocks == [6, 12, 32, 32]:
model = Model(inputs, x, name='densenet169')
elif blocks == [6, 12, 48, 32]:
model = Model(inputs, x, name='densenet201')
else:
model = Model(inputs, x, name='densenet')
# Load weights.
if weights == 'imagenet':
if include_top:
if blocks == [6, 12, 24, 16]:
weights_path = get_file(
'densenet121_weights_tf_dim_ordering_tf_kernels.h5',
DENSENET121_WEIGHT_PATH,
cache_subdir='models',
file_hash='0962ca643bae20f9b6771cb844dca3b0')
elif blocks == [6, 12, 32, 32]:
weights_path = get_file(
'densenet169_weights_tf_dim_ordering_tf_kernels.h5',
DENSENET169_WEIGHT_PATH,
cache_subdir='models',
file_hash='bcf9965cf5064a5f9eb6d7dc69386f43')
elif blocks == [6, 12, 48, 32]:
weights_path = get_file(
'densenet201_weights_tf_dim_ordering_tf_kernels.h5',
DENSENET201_WEIGHT_PATH,
cache_subdir='models',
file_hash='7bb75edd58cb43163be7e0005fbe95ef')
else:
if blocks == [6, 12, 24, 16]:
weights_path = get_file(
'densenet121_weights_tf_dim_ordering_tf_kernels_notop.h5',
DENSENET121_WEIGHT_PATH_NO_TOP,
cache_subdir='models',
file_hash='4912a53fbd2a69346e7f2c0b5ec8c6d3')
elif blocks == [6, 12, 32, 32]:
weights_path = get_file(
'densenet169_weights_tf_dim_ordering_tf_kernels_notop.h5',
DENSENET169_WEIGHT_PATH_NO_TOP,
cache_subdir='models',
file_hash='50662582284e4cf834ce40ab4dfa58c6')
elif blocks == [6, 12, 48, 32]:
weights_path = get_file(
'densenet201_weights_tf_dim_ordering_tf_kernels_notop.h5',
DENSENET201_WEIGHT_PATH_NO_TOP,
cache_subdir='models',
file_hash='1c2de60ee40562448dbac34a0737e798')
model.load_weights(weights_path)
elif weights is not None:
model.load_weights(weights)
return model
def InceptionResNetV2(include_top=True,
weights='imagenet',
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000):
"""Instantiates the Inception-ResNet v2 architecture.
Optionally loads weights pre-trained on ImageNet.
Note that when using TensorFlow, for best performance you should
set `"image_data_format": "channels_last"` in your Keras config
at `~/.keras/keras.json`.
The model and the weights are compatible with both TensorFlow and Theano
backends (but not CNTK). The data format convention used by the model is
the one specified in your Keras config file.
Note that the default input image size for this model is 299x299, instead
of 224x224 as in the VGG16 and ResNet models. Also, the input preprocessing
function is different (i.e., do not use `imagenet_utils.preprocess_input()`
with this model. Use `preprocess_input()` defined in this module instead).
# Arguments
include_top: whether to include the fully-connected
layer at the top of the network.
weights: one of `None` (random initialization)
or `'imagenet'` (pre-training on ImageNet).
input_tensor: optional Keras tensor (i.e. output of `layers.Input()`)
to use as image input for the model.
input_shape: optional shape tuple, only to be specified
if `include_top` is `False` (otherwise the input shape
has to be `(299, 299, 3)` (with `'channels_last'` data format)
or `(3, 299, 299)` (with `'channels_first'` data format).
It should have exactly 3 inputs channels,
and width and height should be no smaller than 139.
E.g. `(150, 150, 3)` would be one valid value.
pooling: Optional pooling mode for feature extraction
when `include_top` is `False`.
- `None` means that the output of the model will be
the 4D tensor output of the last convolutional layer.
- `'avg'` means that global average pooling
will be applied to the output of the
last convolutional layer, and thus
the output of the model will be a 2D tensor.
- `'max'` means that global max pooling will be applied.
classes: optional number of classes to classify images
into, only to be specified if `include_top` is `True`, and
if no `weights` argument is specified.
# Returns
A Keras `Model` instance.
# Raises
ValueError: in case of invalid argument for `weights`,
or invalid input shape.
RuntimeError: If attempting to run this model with an unsupported backend.
"""
if K.backend() in {'cntk'}:
raise RuntimeError(K.backend() + ' backend is currently unsupported for this model.')
if weights not in {'imagenet', None}:
raise ValueError('The `weights` argument should be either '
'`None` (random initialization) or `imagenet` '
'(pre-training on ImageNet).')
if weights == 'imagenet' and include_top and classes != 1000:
raise ValueError('If using `weights` as imagenet with `include_top`'
' as true, `classes` should be 1000')
# Determine proper input shape
input_shape = _obtain_input_shape(
input_shape,
default_size=299,
min_size=139,
data_format=K.image_data_format(),
require_flatten=False,
weights=weights)
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
if not K.is_keras_tensor(input_tensor):
img_input = Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
# Stem block: 35 x 35 x 192
x = conv2d_bn(img_input, 32, 3, strides=2, padding='valid')
x = conv2d_bn(x, 32, 3, padding='valid')
x = conv2d_bn(x, 64, 3)
x = MaxPooling2D(3, strides=2)(x)
x = conv2d_bn(x, 80, 1, padding='valid')
x = conv2d_bn(x, 192, 3, padding='valid')
x = MaxPooling2D(3, strides=2)(x)
# Mixed 5b (Inception-A block): 35 x 35 x 320
branch_0 = conv2d_bn(x, 96, 1)
branch_1 = conv2d_bn(x, 48, 1)
branch_1 = conv2d_bn(branch_1, 64, 5)
branch_2 = conv2d_bn(x, 64, 1)
branch_2 = conv2d_bn(branch_2, 96, 3)
branch_2 = conv2d_bn(branch_2, 96, 3)
branch_pool = AveragePooling2D(3, strides=1, padding='same')(x)
branch_pool = conv2d_bn(branch_pool, 64, 1)
branches = [branch_0, branch_1, branch_2, branch_pool]
channel_axis = 1 if K.image_data_format() == 'channels_first' else 3
x = Concatenate(axis=channel_axis, name='mixed_5b')(branches)
# 10x block35 (Inception-ResNet-A block): 35 x 35 x 320
for block_idx in range(1, 11):
x = inception_resnet_block(x,
scale=0.17,
block_type='block35',
block_idx=block_idx)
# Mixed 6a (Reduction-A block): 17 x 17 x 1088
branch_0 = conv2d_bn(x, 384, 3, strides=2, padding='valid')
branch_1 = conv2d_bn(x, 256, 1)
branch_1 = conv2d_bn(branch_1, 256, 3)
branch_1 = conv2d_bn(branch_1, 384, 3, strides=2, padding='valid')
branch_pool = MaxPooling2D(3, strides=2, padding='valid')(x)
branches = [branch_0, branch_1, branch_pool]
x = Concatenate(axis=channel_axis, name='mixed_6a')(branches)
# 20x block17 (Inception-ResNet-B block): 17 x 17 x 1088
for block_idx in range(1, 21):
x = inception_resnet_block(x,
scale=0.1,
block_type='block17',
block_idx=block_idx)
# Mixed 7a (Reduction-B block): 8 x 8 x 2080
branch_0 = conv2d_bn(x, 256, 1)
branch_0 = conv2d_bn(branch_0, 384, 3, strides=2, padding='valid')
branch_1 = conv2d_bn(x, 256, 1)
branch_1 = conv2d_bn(branch_1, 288, 3, strides=2, padding='valid')
branch_2 = conv2d_bn(x, 256, 1)
branch_2 = conv2d_bn(branch_2, 288, 3)
branch_2 = conv2d_bn(branch_2, 320, 3, strides=2, padding='valid')
branch_pool = MaxPooling2D(3, strides=2, padding='valid')(x)
branches = [branch_0, branch_1, branch_2, branch_pool]
x = Concatenate(axis=channel_axis, name='mixed_7a')(branches)
# 10x block8 (Inception-ResNet-C block): 8 x 8 x 2080
for block_idx in range(1, 10):
x = inception_resnet_block(x,
scale=0.2,
block_type='block8',
block_idx=block_idx)
x = inception_resnet_block(x,
scale=1.,
activation=None,
block_type='block8',
block_idx=10)
# Final convolution block: 8 x 8 x 1536
x = conv2d_bn(x, 1536, 1, name='conv_7b')
if include_top:
# Classification block
x = GlobalAveragePooling2D(name='avg_pool')(x)
x = Dense(classes, activation='softmax', name='predictions')(x)
else:
if pooling == 'avg':
x = GlobalAveragePooling2D()(x)
elif pooling == 'max':
x = GlobalMaxPooling2D()(x)
# Ensure that the model takes into account
# any potential predecessors of `input_tensor`
if input_tensor is not None:
inputs = get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model
model = Model(inputs, x, name='inception_resnet_v2')
# Load weights
if weights == 'imagenet':
if K.image_data_format() == 'channels_first':
if K.backend() == 'tensorflow':
warnings.warn('You are using the TensorFlow backend, yet you '
'are using the Theano '
'image data format convention '
'(`image_data_format="channels_first"`). '
'For best performance, set '
'`image_data_format="channels_last"` in '
'your Keras config '
'at ~/.keras/keras.json.')
if include_top:
weights_filename = 'inception_resnet_v2_weights_tf_dim_ordering_tf_kernels.h5'
weights_path = get_file(weights_filename,
BASE_WEIGHT_URL + weights_filename,
cache_subdir='models',
md5_hash='e693bd0210a403b3192acc6073ad2e96')
else:
weights_filename = 'inception_resnet_v2_weights_tf_dim_ordering_tf_kernels_notop.h5'
weights_path = get_file(weights_filename,
BASE_WEIGHT_URL + weights_filename,
cache_subdir='models',
md5_hash='d19885ff4a710c122648d3b5c3b684e4')
model.load_weights(weights_path)
return model
def MobileNet(input_shape=None,
alpha=1.0,
depth_multiplier=1,
dropout=1e-3,
include_top=True,
weights='imagenet',
input_tensor=None,
pooling=None,
classes=1000):
"""Instantiates the MobileNet architecture.
Note that only TensorFlow is supported for now,
therefore it only works with the data format
`image_data_format='channels_last'` in your Keras config
at `~/.keras/keras.json`.
To load a MobileNet model via `load_model`, import the custom
objects `relu6` and `DepthwiseConv2D` and pass them to the
`custom_objects` parameter.
E.g.
model = load_model('mobilenet.h5', custom_objects={
'relu6': mobilenet.relu6,
'DepthwiseConv2D': mobilenet.DepthwiseConv2D})
# Arguments
input_shape: optional shape tuple, only to be specified
if `include_top` is False (otherwise the input shape
has to be `(224, 224, 3)` (with `channels_last` data format)
or (3, 224, 224) (with `channels_first` data format).
It should have exactly 3 inputs channels,
and width and height should be no smaller than 32.
E.g. `(200, 200, 3)` would be one valid value.
alpha: controls the width of the network.
- If `alpha` < 1.0, proportionally decreases the number
of filters in each layer.
- If `alpha` > 1.0, proportionally increases the number
of filters in each layer.
- If `alpha` = 1, default number of filters from the paper
are used at each layer.
depth_multiplier: depth multiplier for depthwise convolution
(also called the resolution multiplier)
dropout: dropout rate
include_top: whether to include the fully-connected
layer at the top of the network.
weights: `None` (random initialization) or
`imagenet` (ImageNet weights)
input_tensor: optional Keras tensor (i.e. output of
`layers.Input()`)
to use as image input for the model.
pooling: Optional pooling mode for feature extraction
when `include_top` is `False`.
- `None` means that the output of the model
will be the 4D tensor output of the
last convolutional layer.
- `avg` means that global average pooling
will be applied to the output of the
last convolutional layer, and thus
the output of the model will be a
2D tensor.
- `max` means that global max pooling will
be applied.
classes: optional number of classes to classify images
into, only to be specified if `include_top` is True, and
if no `weights` argument is specified.
# Returns
A Keras model instance.
# Raises
ValueError: in case of invalid argument for `weights`,
or invalid input shape.
RuntimeError: If attempting to run this model with a
backend that does not support separable convolutions.
"""
if K.backend() != 'tensorflow':
raise RuntimeError('Only Tensorflow backend is currently supported, '
'as other backends do not support '
'depthwise convolution.')
if weights not in {'imagenet', None}:
raise ValueError('The `weights` argument should be either '
'`None` (random initialization) or `imagenet` '
'(pre-training on ImageNet).')
if weights == 'imagenet' and include_top and classes != 1000:
raise ValueError('If using `weights` as ImageNet with `include_top` '
'as true, `classes` should be 1000')
# Determine proper input shape.
input_shape = _obtain_input_shape(input_shape,
default_size=224,
min_size=32,
data_format=K.image_data_format(),
include_top=include_top or weights)
if K.image_data_format() == 'channels_last':
row_axis, col_axis = (0, 1)
else:
row_axis, col_axis = (1, 2)
rows = input_shape[row_axis]
cols = input_shape[col_axis]
if weights == 'imagenet':
if depth_multiplier != 1:
raise ValueError('If imagenet weights are being loaded, '
'depth multiplier must be 1')
if alpha not in [0.25, 0.50, 0.75, 1.0]:
raise ValueError('If imagenet weights are being loaded, '
'alpha can be one of'
'`0.25`, `0.50`, `0.75` or `1.0` only.')
if rows != cols or rows not in [128, 160, 192, 224]:
raise ValueError('If imagenet weights are being loaded, '
'input must have a static square shape (one of '
'(128,128), (160,160), (192,192), or (224, 224)).'
' Input shape provided = %s' % (input_shape,))
if K.image_data_format() != 'channels_last':
warnings.warn('The MobileNet family of models is only available '
'for the input data format "channels_last" '
'(width, height, channels). '
'However your settings specify the default '
'data format "channels_first" (channels, width, height).'
' You should set `image_data_format="channels_last"` '
'in your Keras config located at ~/.keras/keras.json. '
'The model being returned right now will expect inputs '
'to follow the "channels_last" data format.')
K.set_image_data_format('channels_last')
old_data_format = 'channels_first'
else:
old_data_format = None
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
if not K.is_keras_tensor(input_tensor):
img_input = Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
x = _conv_block(img_input, 32, alpha, strides=(2, 2))
x = _depthwise_conv_block(x, 64, alpha, depth_multiplier, block_id=1)
x = _depthwise_conv_block(x, 128, alpha, depth_multiplier,
strides=(2, 2), block_id=2)
x = _depthwise_conv_block(x, 128, alpha, depth_multiplier, block_id=3)
x = _depthwise_conv_block(x, 256, alpha, depth_multiplier,
strides=(2, 2), block_id=4)
x = _depthwise_conv_block(x, 256, alpha, depth_multiplier, block_id=5)
x = _depthwise_conv_block(x, 512, alpha, depth_multiplier,
strides=(2, 2), block_id=6)
x = _depthwise_conv_block(x, 512, alpha, depth_multiplier, block_id=7)
x = _depthwise_conv_block(x, 512, alpha, depth_multiplier, block_id=8)
x = _depthwise_conv_block(x, 512, alpha, depth_multiplier, block_id=9)
x = _depthwise_conv_block(x, 512, alpha, depth_multiplier, block_id=10)
x = _depthwise_conv_block(x, 512, alpha, depth_multiplier, block_id=11)
x = _depthwise_conv_block(x, 1024, alpha, depth_multiplier,
strides=(2, 2), block_id=12)
x = _depthwise_conv_block(x, 1024, alpha, depth_multiplier, block_id=13)
if include_top:
if K.image_data_format() == 'channels_first':
shape = (int(1024 * alpha), 1, 1)
else:
shape = (1, 1, int(1024 * alpha))
x = GlobalAveragePooling2D()(x)
x = Reshape(shape, name='reshape_1')(x)
x = Dropout(dropout, name='dropout')(x)
x = Conv2D(classes, (1, 1),
padding='same', name='conv_preds')(x)
x = Activation('softmax', name='act_softmax')(x)
x = Reshape((classes,), name='reshape_2')(x)
else:
if pooling == 'avg':
x = GlobalAveragePooling2D()(x)
elif pooling == 'max':
x = GlobalMaxPooling2D()(x)
# Ensure that the model takes into account
# any potential predecessors of `input_tensor`.
if input_tensor is not None:
inputs = get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model.
model = Model(inputs, x, name='mobilenet_%0.2f_%s' % (alpha, rows))
# load weights
if weights == 'imagenet':
if K.image_data_format() == 'channels_first':
raise ValueError('Weights for "channels_last" format '
'are not available.')
if alpha == 1.0:
alpha_text = '1_0'
elif alpha == 0.75:
alpha_text = '7_5'
elif alpha == 0.50:
alpha_text = '5_0'
else:
alpha_text = '2_5'
if include_top:
model_name = 'mobilenet_%s_%d_tf.h5' % (alpha_text, rows)
weigh_path = BASE_WEIGHT_PATH + model_name
weights_path = get_file(model_name,
weigh_path,
cache_subdir='models')
else:
model_name = 'mobilenet_%s_%d_tf_no_top.h5' % (alpha_text, rows)
weigh_path = BASE_WEIGHT_PATH + model_name
weights_path = get_file(model_name,
weigh_path,
cache_subdir='models')
model.load_weights(weights_path)
if old_data_format:
K.set_image_data_format(old_data_format)
return model
def MusicTaggerCRNN(weights='msd', input_tensor=None, include_top=True):
'''Instantiate the MusicTaggerCRNN architecture,
optionally loading weights pre-trained
on Million Song Dataset. Note that when using TensorFlow,
for best performance you should set
`image_dim_ordering="tf"` in your Keras config
at ~/.keras/keras.json.
The model and the weights are compatible with both
TensorFlow and Theano. The dimension ordering
convention used by the model is the one
specified in your Keras config file.
For preparing mel-spectrogram input, see
`audio_conv_utils.py` in [applications](https://github.com/fchollet/keras/tree/master/keras/applications).
You will need to install [Librosa](http://librosa.github.io/librosa/)
to use it.
# Arguments
weights: one of `None` (random initialization)
or "msd" (pre-training on ImageNet).
input_tensor: optional Keras tensor (i.e. output of `layers.Input()`)
to use as image input for the model.
include_top: whether to include the 1 fully-connected
layer (output layer) at the top of the network.
If False, the network outputs 32-dim features.
# Returns
A Keras model instance.
'''
if weights not in {'msd', None}:
raise ValueError('The `weights` argument should be either '
'`None` (random initialization) or `msd` '
'(pre-training on Million Song Dataset).')
# Determine proper input shape
if K.image_dim_ordering() == 'th':
input_shape = (1, 96, 1366)
else:
input_shape = (96, 1366, 1)
if input_tensor is None:
melgram_input = Input(shape=input_shape)
else:
if not K.is_keras_tensor(input_tensor):
melgram_input = Input(tensor=input_tensor, shape=input_shape)
else:
melgram_input = input_tensor
# Determine input axis
if K.image_dim_ordering() == 'th':
channel_axis = 1
freq_axis = 2
time_axis = 3
else:
channel_axis = 3
freq_axis = 1
time_axis = 2
# Input block
x = ZeroPadding2D(padding=(0, 37))(melgram_input)
x = BatchNormalization(axis=freq_axis, name='bn_0_freq')(x)
# Conv block 1
x = Convolution2D(64, 3, 3, border_mode='same', name='conv1')(x)
x = BatchNormalization(axis=channel_axis, mode=0, name='bn1')(x)
x = ELU()(x)
x = MaxPooling2D(pool_size=(2, 2), strides=(2, 2), name='pool1')(x)
x = Dropout(0.1, name='dropout1')(x)
# Conv block 2
x = Convolution2D(128, 3, 3, border_mode='same', name='conv2')(x)
x = BatchNormalization(axis=channel_axis, mode=0, name='bn2')(x)
x = ELU()(x)
x = MaxPooling2D(pool_size=(3, 3), strides=(3, 3), name='pool2')(x)
x = Dropout(0.1, name='dropout2')(x)
# Conv block 3
x = Convolution2D(128, 3, 3, border_mode='same', name='conv3')(x)
x = BatchNormalization(axis=channel_axis, mode=0, name='bn3')(x)
x = ELU()(x)
x = MaxPooling2D(pool_size=(4, 4), strides=(4, 4), name='pool3')(x)
x = Dropout(0.1, name='dropout3')(x)
# Conv block 4
x = Convolution2D(128, 3, 3, border_mode='same', name='conv4')(x)
x = BatchNormalization(axis=channel_axis, mode=0, name='bn4')(x)
x = ELU()(x)
x = MaxPooling2D(pool_size=(4, 4), strides=(4, 4), name='pool4')(x)
x = Dropout(0.1, name='dropout4')(x)
# reshaping
if K.image_dim_ordering() == 'th':
x = Permute((3, 1, 2))(x)
x = Reshape((15, 128))(x)
# GRU block 1, 2, output
x = GRU(32, return_sequences=True, name='gru1')(x)
x = GRU(32, return_sequences=False, name='gru2')(x)
x = Dropout(0.3)(x)
if include_top:
x = Dense(50, activation='sigmoid', name='output')(x)
# Create model
model = Model(melgram_input, x)
if weights is None:
return model
else:
# Load input
if K.image_dim_ordering() == 'tf':
raise RuntimeError("Please set image_dim_ordering == 'th'."
"You can set it at ~/.keras/keras.json")
model.load_weights('data/music_tagger_crnn_weights_%s.h5' % K._BACKEND,
by_name=True)
return model
def VGG19(include_top=True, weights='imagenet',
input_tensor=None, input_shape=None,
pooling=None,
classes=1000):
"""Instantiates the VGG19 architecture.
Optionally loads weights pre-trained
on ImageNet. Note that when using TensorFlow,
for best performance you should set
`image_data_format="channels_last"` in your Keras config
at ~/.keras/keras.json.
The model and the weights are compatible with both
TensorFlow and Theano. The data format
convention used by the model is the one
specified in your Keras config file.
# Arguments
include_top: whether to include the 3 fully-connected
layers at the top of the network.
weights: one of `None` (random initialization)
or "imagenet" (pre-training on ImageNet).
input_tensor: optional Keras tensor (i.e. output of `layers.Input()`)
to use as image input for the model.
input_shape: optional shape tuple, only to be specified
if `include_top` is False (otherwise the input shape
has to be `(224, 224, 3)` (with `channels_last` data format)
or `(3, 224, 244)` (with `channels_first` data format).
It should have exactly 3 inputs channels,
and width and height should be no smaller than 48.
E.g. `(200, 200, 3)` would be one valid value.
pooling: Optional pooling mode for feature extraction
when `include_top` is `False`.
- `None` means that the output of the model will be
the 4D tensor output of the
last convolutional layer.
- `avg` means that global average pooling
will be applied to the output of the
last convolutional layer, and thus
the output of the model will be a 2D tensor.
- `max` means that global max pooling will
be applied.
classes: optional number of classes to classify images
into, only to be specified if `include_top` is True, and
if no `weights` argument is specified.
# Returns
A Keras model instance.
# Raises
ValueError: in case of invalid argument for `weights`,
or invalid input shape.
"""
if weights not in {'imagenet', None}:
raise ValueError('The `weights` argument should be either '
'`None` (random initialization) or `imagenet` '
'(pre-training on ImageNet).')
if weights == 'imagenet' and include_top and classes != 1000:
raise ValueError('If using `weights` as imagenet with `include_top`'
' as true, `classes` should be 1000')
# Determine proper input shape
input_shape = _obtain_input_shape(input_shape,
default_size=224,
min_size=48,
data_format=K.image_data_format(),
include_top=include_top)
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
if not K.is_keras_tensor(input_tensor):
img_input = Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
# Block 1
x = Conv2D(64, (3, 3), activation='relu', padding='same', name='block1_conv1')(img_input)
x = Conv2D(64, (3, 3), activation='relu', padding='same', name='block1_conv2')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='block1_pool')(x)
# Block 2
x = Conv2D(128, (3, 3), activation='relu', padding='same', name='block2_conv1')(x)
x = Conv2D(128, (3, 3), activation='relu', padding='same', name='block2_conv2')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='block2_pool')(x)
# Block 3
x = Conv2D(256, (3, 3), activation='relu', padding='same', name='block3_conv1')(x)
x = Conv2D(256, (3, 3), activation='relu', padding='same', name='block3_conv2')(x)
x = Conv2D(256, (3, 3), activation='relu', padding='same', name='block3_conv3')(x)
x = Conv2D(256, (3, 3), activation='relu', padding='same', name='block3_conv4')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='block3_pool')(x)
# Block 4
x = Conv2D(512, (3, 3), activation='relu', padding='same', name='block4_conv1')(x)
x = Conv2D(512, (3, 3), activation='relu', padding='same', name='block4_conv2')(x)
x = Conv2D(512, (3, 3), activation='relu', padding='same', name='block4_conv3')(x)
x = Conv2D(512, (3, 3), activation='relu', padding='same', name='block4_conv4')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='block4_pool')(x)
# Block 5
x = Conv2D(512, (3, 3), activation='relu', padding='same', name='block5_conv1')(x)
x = Conv2D(512, (3, 3), activation='relu', padding='same', name='block5_conv2')(x)
x = Conv2D(512, (3, 3), activation='relu', padding='same', name='block5_conv3')(x)
x = Conv2D(512, (3, 3), activation='relu', padding='same', name='block5_conv4')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='block5_pool')(x)
if include_top:
# Classification block
x = Flatten(name='flatten')(x)
x = Dense(4096, activation='relu', name='fc1')(x)
x = Dense(4096, activation='relu', name='fc2')(x)
x = Dense(classes, activation='softmax', name='predictions')(x)
else:
if pooling == 'avg':
x = GlobalAveragePooling2D()(x)
elif pooling == 'max':
x = GlobalMaxPooling2D()(x)
# Ensure that the model takes into account
# any potential predecessors of `input_tensor`.
if input_tensor is not None:
inputs = get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model.
model = Model(inputs, x, name='vgg19')
# load weights
if weights == 'imagenet':
if include_top:
weights_path = get_file('vgg19_weights_tf_dim_ordering_tf_kernels.h5',
WEIGHTS_PATH,
cache_subdir='models')
else:
weights_path = get_file('vgg19_weights_tf_dim_ordering_tf_kernels_notop.h5',
WEIGHTS_PATH_NO_TOP,
cache_subdir='models')
model.load_weights(weights_path)
if K.backend() == 'theano':
layer_utils.convert_all_kernels_in_model(model)
if K.image_data_format() == 'channels_first':
if include_top:
maxpool = model.get_layer(name='block5_pool')
shape = maxpool.output_shape[1:]
dense = model.get_layer(name='fc1')
layer_utils.convert_dense_weights_data_format(dense, shape, 'channels_first')
if K.backend() == 'tensorflow':
warnings.warn('You are using the TensorFlow backend, yet you '
'are using the Theano '
'image data format convention '
'(`image_data_format="channels_first"`). '
'For best performance, set '
'`image_data_format="channels_last"` in '
'your Keras config '
'at ~/.keras/keras.json.')
return model
def DenseNet(input_shape=None,
depth=40,
nb_dense_block=3,
growth_rate=12,
nb_filter=-1,
nb_layers_per_block=-1,
bottleneck=False,
reduction=0.0,
dropout_rate=0.0,
weight_decay=1e-4,
subsample_initial_block=False,
include_top=True,
weights=None,
input_tensor=None,
classes=10,
activation='softmax'):
"""Instantiate the DenseNet architecture,
optionally loading weights pre-trained
on CIFAR-10. Note that when using TensorFlow,
for best performance you should set
`image_data_format='channels_last'` in your Keras config
at ~/.keras/keras.json.
The model and the weights are compatible with both
TensorFlow and Theano. The dimension ordering
convention used by the model is the one
specified in your Keras config file.
# Arguments
input_shape: optional shape tuple, only to be specified
if `include_top` is False (otherwise the input shape
has to be `(32, 32, 3)` (with `channels_last` dim ordering)
or `(3, 32, 32)` (with `channels_first` dim ordering).
It should have exactly 3 inputs channels,
and width and height should be no smaller than 8.
E.g. `(200, 200, 3)` would be one valid value.
depth: number or layers in the DenseNet
nb_dense_block: number of dense blocks to add to end (generally = 3)
growth_rate: number of filters to add per dense block
nb_filter: initial number of filters. -1 indicates initial
number of filters is 2 * growth_rate
nb_layers_per_block: number of layers in each dense block.
Can be a -1, positive integer or a list.
If -1, calculates nb_layer_per_block from the network depth.
If positive integer, a set number of layers per dense block.
If list, nb_layer is used as provided. Note that list size must
be (nb_dense_block + 1)
bottleneck: flag to add bottleneck blocks in between dense blocks
reduction: reduction factor of transition blocks.
Note : reduction value is inverted to compute compression.
dropout_rate: dropout rate
weight_decay: weight decay rate
subsample_initial_block: Set to True to subsample the initial convolution and
add a MaxPool2D before the dense blocks are added.
include_top: whether to include the fully-connected
layer at the top of the network.
weights: one of `None` (random initialization) or
'imagenet' (pre-training on ImageNet)..
input_tensor: optional Keras tensor (i.e. output of `layers.Input()`)
to use as image input for the model.
classes: optional number of classes to classify images
into, only to be specified if `include_top` is True, and
if no `weights` argument is specified.
activation: Type of activation at the top layer. Can be one of 'softmax' or 'sigmoid'.
Note that if sigmoid is used, classes must be 1.
# Returns
A Keras model instance.
"""
if weights not in {'imagenet', None}:
raise ValueError('The `weights` argument should be either '
'`None` (random initialization) or `cifar10` '
'(pre-training on CIFAR-10).')
if weights == 'imagenet' and include_top and classes != 1000:
raise ValueError('If using `weights` as ImageNet with `include_top`'
' as true, `classes` should be 1000')
if activation not in ['softmax', 'sigmoid']:
raise ValueError('activation must be one of "softmax" or "sigmoid"')
if activation == 'sigmoid' and classes != 1:
raise ValueError(
'sigmoid activation can only be used when classes = 1')
# Determine proper input shape
input_shape = _obtain_input_shape(input_shape,
default_size=32,
min_size=8,
data_format=K.image_data_format(),
require_flatten=include_top)
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
if not K.is_keras_tensor(input_tensor):
img_input = Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
x = __create_dense_net(classes, img_input, include_top, depth,
nb_dense_block, growth_rate, nb_filter,
nb_layers_per_block, bottleneck, reduction,
dropout_rate, weight_decay, subsample_initial_block,
activation)
# Ensure that the model takes into account
# any potential predecessors of `input_tensor`.
if input_tensor is not None:
inputs = get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model.
model = Model(inputs, x, name='densenet')
return model
def Deeplabv3(weights='pascal_voc', input_tensor=None, input_shape=(512, 512, 3), classes=21, backbone='mobilenetv2', OS=16, alpha=1.):
""" Instantiates the Deeplabv3+ architecture
Optionally loads weights pre-trained
on PASCAL VOC. This model is available for TensorFlow only,
and can only be used with inputs following the TensorFlow
data format `(width, height, channels)`.
# Arguments
weights: one of 'pascal_voc' (pre-trained on pascal voc)
or None (random initialization)
input_tensor: optional Keras tensor (i.e. output of `layers.Input()`)
to use as image input for the model.
input_shape: shape of input image. format HxWxC
PASCAL VOC model was trained on (512,512,3) images
classes: number of desired classes. If classes != 21,
last layer is initialized randomly
backbone: backbone to use. one of {'xception','mobilenetv2'}
OS: determines input_shape/feature_extractor_output ratio. One of {8,16}.
Used only for xception backbone.
alpha: controls the width of the MobileNetV2 network. This is known as the
width multiplier in the MobileNetV2 paper.
- If `alpha` < 1.0, proportionally decreases the number
of filters in each layer.
- If `alpha` > 1.0, proportionally increases the number
of filters in each layer.
- If `alpha` = 1, default number of filters from the paper
are used at each layer.
Used only for mobilenetv2 backbone
# Returns
A Keras model instance.
# Raises
RuntimeError: If attempting to run this model with a
backend that does not support separable convolutions.
ValueError: in case of invalid argument for `weights` or `backbone`
"""
if not (weights in {'pascal_voc', None}):
raise ValueError('The `weights` argument should be either '
'`None` (random initialization) or `pascal_voc` '
'(pre-trained on PASCAL VOC)')
if K.backend() != 'tensorflow':
raise RuntimeError('The Deeplabv3+ model is only available with '
'the TensorFlow backend.')
if not (backbone in {'xception', 'mobilenetv2'}):
raise ValueError('The `backbone` argument should be either '
'`xception` or `mobilenetv2` ')
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
if not K.is_keras_tensor(input_tensor):
img_input = Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
if backbone == 'xception':
if OS == 8:
entry_block3_stride = 1
middle_block_rate = 2 # ! Not mentioned in paper, but required
exit_block_rates = (2, 4)
atrous_rates = (12, 24, 36)
else:
entry_block3_stride = 2
middle_block_rate = 1
exit_block_rates = (1, 2)
atrous_rates = (6, 12, 18)
x = Conv2D(32, (3, 3), strides=(2, 2),
name='entry_flow_conv1_1', use_bias=False, padding='same')(img_input)
x = BatchNormalization(name='entry_flow_conv1_1_BN')(x)
x = Activation('relu')(x)
x = _conv2d_same(x, 64, 'entry_flow_conv1_2', kernel_size=3, stride=1)
x = BatchNormalization(name='entry_flow_conv1_2_BN')(x)
x = Activation('relu')(x)
x = _xception_block(x, [128, 128, 128], 'entry_flow_block1',
skip_connection_type='conv', stride=2,
depth_activation=False)
x, skip1 = _xception_block(x, [256, 256, 256], 'entry_flow_block2',
skip_connection_type='conv', stride=2,
depth_activation=False, return_skip=True)
x = _xception_block(x, [728, 728, 728], 'entry_flow_block3',
skip_connection_type='conv', stride=entry_block3_stride,
depth_activation=False)
for i in range(16):
x = _xception_block(x, [728, 728, 728], 'middle_flow_unit_{}'.format(i + 1),
skip_connection_type='sum', stride=1, rate=middle_block_rate,
depth_activation=False)
x = _xception_block(x, [728, 1024, 1024], 'exit_flow_block1',
skip_connection_type='conv', stride=1, rate=exit_block_rates[0],
depth_activation=False)
x = _xception_block(x, [1536, 1536, 2048], 'exit_flow_block2',
skip_connection_type='none', stride=1, rate=exit_block_rates[1],
depth_activation=True)
else:
OS = 8
first_block_filters = _make_divisible(32 * alpha, 8)
x = Conv2D(first_block_filters,
kernel_size=3,
strides=(2, 2), padding='same',
use_bias=False, name='Conv')(img_input)
x = BatchNormalization(
epsilon=1e-3, momentum=0.999, name='Conv_BN')(x)
x = Activation(relu6, name='Conv_Relu6')(x)
x = _inverted_res_block(x, filters=16, alpha=alpha, stride=1,
expansion=1, block_id=0, skip_connection=False)
x = _inverted_res_block(x, filters=24, alpha=alpha, stride=2,
expansion=6, block_id=1, skip_connection=False)
x = _inverted_res_block(x, filters=24, alpha=alpha, stride=1,
expansion=6, block_id=2, skip_connection=True)
x = _inverted_res_block(x, filters=32, alpha=alpha, stride=2,
expansion=6, block_id=3, skip_connection=False)
x = _inverted_res_block(x, filters=32, alpha=alpha, stride=1,
expansion=6, block_id=4, skip_connection=True)
x = _inverted_res_block(x, filters=32, alpha=alpha, stride=1,
expansion=6, block_id=5, skip_connection=True)
# stride in block 6 changed from 2 -> 1, so we need to use rate = 2
x = _inverted_res_block(x, filters=64, alpha=alpha, stride=1, # 1!
expansion=6, block_id=6, skip_connection=False)
x = _inverted_res_block(x, filters=64, alpha=alpha, stride=1, rate=2,
expansion=6, block_id=7, skip_connection=True)
x = _inverted_res_block(x, filters=64, alpha=alpha, stride=1, rate=2,
expansion=6, block_id=8, skip_connection=True)
x = _inverted_res_block(x, filters=64, alpha=alpha, stride=1, rate=2,
expansion=6, block_id=9, skip_connection=True)
x = _inverted_res_block(x, filters=96, alpha=alpha, stride=1, rate=2,
expansion=6, block_id=10, skip_connection=False)
x = _inverted_res_block(x, filters=96, alpha=alpha, stride=1, rate=2,
expansion=6, block_id=11, skip_connection=True)
x = _inverted_res_block(x, filters=96, alpha=alpha, stride=1, rate=2,
expansion=6, block_id=12, skip_connection=True)
x = _inverted_res_block(x, filters=160, alpha=alpha, stride=1, rate=2, # 1!
expansion=6, block_id=13, skip_connection=False)
x = _inverted_res_block(x, filters=160, alpha=alpha, stride=1, rate=4,
expansion=6, block_id=14, skip_connection=True)
x = _inverted_res_block(x, filters=160, alpha=alpha, stride=1, rate=4,
expansion=6, block_id=15, skip_connection=True)
x = _inverted_res_block(x, filters=320, alpha=alpha, stride=1, rate=4,
expansion=6, block_id=16, skip_connection=False)
# end of feature extractor
# branching for Atrous Spatial Pyramid Pooling
# Image Feature branch
#out_shape = int(np.ceil(input_shape[0] / OS))
b4 = AveragePooling2D(pool_size=(int(np.ceil(input_shape[0] / OS)), int(np.ceil(input_shape[1] / OS))))(x)
b4 = Conv2D(256, (1, 1), padding='same',
use_bias=False, name='image_pooling')(b4)
b4 = BatchNormalization(name='image_pooling_BN', epsilon=1e-5)(b4)
b4 = Activation('relu')(b4)
b4 = BilinearUpsampling((int(np.ceil(input_shape[0] / OS)), int(np.ceil(input_shape[1] / OS))))(b4)
# simple 1x1
b0 = Conv2D(256, (1, 1), padding='same', use_bias=False, name='aspp0')(x)
b0 = BatchNormalization(name='aspp0_BN', epsilon=1e-5)(b0)
b0 = Activation('relu', name='aspp0_activation')(b0)
# there are only 2 branches in mobilenetV2. not sure why
if backbone == 'xception':
# rate = 6 (12)
b1 = SepConv_BN(x, 256, 'aspp1',
rate=atrous_rates[0], depth_activation=True, epsilon=1e-5)
# rate = 12 (24)
b2 = SepConv_BN(x, 256, 'aspp2',
rate=atrous_rates[1], depth_activation=True, epsilon=1e-5)
# rate = 18 (36)
b3 = SepConv_BN(x, 256, 'aspp3',
rate=atrous_rates[2], depth_activation=True, epsilon=1e-5)
# concatenate ASPP branches & project
x = Concatenate()([b4, b0, b1, b2, b3])
else:
x = Concatenate()([b4, b0])
x = Conv2D(256, (1, 1), padding='same',
use_bias=False, name='concat_projection')(x)
x = BatchNormalization(name='concat_projection_BN', epsilon=1e-5)(x)
x = Activation('relu')(x)
x = Dropout(0.1)(x)
# DeepLab v.3+ decoder
if backbone == 'xception':
# Feature projection
# x4 (x2) block
x = BilinearUpsampling(output_size=(int(np.ceil(input_shape[0] / 4)),
int(np.ceil(input_shape[1] / 4))))(x)
dec_skip1 = Conv2D(48, (1, 1), padding='same',
use_bias=False, name='feature_projection0')(skip1)
dec_skip1 = BatchNormalization(
name='feature_projection0_BN', epsilon=1e-5)(dec_skip1)
dec_skip1 = Activation('relu')(dec_skip1)
x = Concatenate()([x, dec_skip1])
x = SepConv_BN(x, 256, 'decoder_conv0',
depth_activation=True, epsilon=1e-5)
x = SepConv_BN(x, 256, 'decoder_conv1',
depth_activation=True, epsilon=1e-5)
# you can use it with arbitary number of classes
if classes == 21:
last_layer_name = 'logits_semantic'
else:
last_layer_name = 'custom_logits_semantic'
x = Conv2D(classes, (1, 1), padding='same', name=last_layer_name)(x)
x = BilinearUpsampling(output_size=(input_shape[0], input_shape[1]))(x)
# Ensure that the model takes into account
# any potential predecessors of `input_tensor`.
if input_tensor is not None:
inputs = get_source_inputs(input_tensor)
else:
inputs = img_input
model = Model(inputs, x, name='deeplabv3plus')
# load weights
if weights == 'pascal_voc':
if backbone == 'xception':
weights_path = get_file('deeplabv3_xception_tf_dim_ordering_tf_kernels.h5',
WEIGHTS_PATH_X,
cache_subdir='models')
else:
weights_path = get_file('deeplabv3_mobilenetv2_tf_dim_ordering_tf_kernels.h5',
WEIGHTS_PATH_MOBILE,
cache_subdir='models')
model.load_weights(weights_path, by_name=True)
return model
def InceptionResNetV2(include_top=True,
weights='imagenet',
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000,
dropout_keep_prob=0.8):
"""Instantiates the Inception-ResNet v2 architecture.
Optionally loads weights pre-trained
on ImageNet. Note that when using TensorFlow,
for best performance you should set
`image_data_format="channels_last"` in your Keras config
at ~/.keras/keras.json.
The model and the weights are compatible with both
TensorFlow and Theano. The data format
convention used by the model is the one
specified in your Keras config file.
Note that the default input image size for this model is 299x299.
# Arguments
include_top: whether to include the fully-connected
layer at the top of the network.
weights: one of `None` (random initialization)
or "imagenet" (pre-training on ImageNet).
input_tensor: optional Keras tensor (i.e. output of `layers.Input()`)
to use as image input for the model.
input_shape: optional shape tuple, only to be specified
if `include_top` is False (otherwise the input shape
has to be `(299, 299, 3)` (with `channels_last` data format)
or `(3, 299, 299)` (with `channels_first` data format).
It should have exactly 3 inputs channels,
and width and height should be no smaller than 139.
E.g. `(150, 150, 3)` would be one valid value.
pooling: Optional pooling mode for feature extraction
when `include_top` is `False`.
- `None` means that the output of the model will be
the 4D tensor output of the
last convolutional layer.
- `avg` means that global average pooling
will be applied to the output of the
last convolutional layer, and thus
the output of the model will be a 2D tensor.
- `max` means that global max pooling will
be applied.
classes: optional number of classes to classify images
into, only to be specified if `include_top` is `True`, and
if no `weights` argument is specified.
dropout_keep_prob: dropout keep rate after pooling and before the
classification layer, only to be specified if `include_top` is `True`.
# Returns
A Keras model instance.
# Raises
ValueError: in case of invalid argument for `weights`,
or invalid input shape.
"""
if weights not in {'imagenet', None}:
raise ValueError('The `weights` argument should be either '
'`None` (random initialization) or `imagenet` '
'(pre-training on ImageNet).')
if weights == 'imagenet' and include_top and classes != 1000:
raise ValueError('If using `weights` as imagenet with `include_top`'
' as true, `classes` should be 1000')
# Determine proper input shape
input_shape = _obtain_input_shape(
input_shape,
default_size=299,
min_size=139,
data_format=K.image_data_format(),
include_top=include_top)
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
if not K.is_keras_tensor(input_tensor):
img_input = Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
if K.image_data_format() == 'channels_first':
channel_axis = 1
else:
channel_axis = 3
# stem block: 35 x 35 x 192
x = conv2d_bn(img_input, 32, 3, strides=2, padding='valid', name='Conv2d_1a_3x3')
x = conv2d_bn(x, 32, 3, padding='valid', name='Conv2d_2a_3x3')
x = conv2d_bn(x, 64, 3, name='Conv2d_2b_3x3')
x = MaxPooling2D(3, strides=2, name='MaxPool_3a_3x3')(x)
x = conv2d_bn(x, 80, 1, padding='valid', name='Conv2d_3b_1x1')
x = conv2d_bn(x, 192, 3, padding='valid', name='Conv2d_4a_3x3')
x = MaxPooling2D(3, strides=2, name='MaxPool_5a_3x3')(x)
# mixed 5b (Inception-A block): 35 x 35 x 320
name_fmt = 'Mixed_5b_Branch_{}_{}'
branch_idx = 0
tower_conv = conv2d_bn(x, 96, 1, name=name_fmt.format(branch_idx, 'Conv2d_1x1'))
branch_idx = 1
tower_conv1_0 = conv2d_bn(x, 48, 1, name=name_fmt.format(branch_idx, 'Conv2d_0a_1x1'))
tower_conv1_1 = conv2d_bn(tower_conv1_0, 64, 5, name=name_fmt.format(branch_idx, 'Conv2d_0b_5x5'))
branch_idx = 2
tower_conv2_0 = conv2d_bn(x, 64, 1, name=name_fmt.format(branch_idx, 'Conv2d_0a_1x1'))
tower_conv2_1 = conv2d_bn(tower_conv2_0, 96, 3, name=name_fmt.format(branch_idx, 'Conv2d_0b_3x3'))
tower_conv2_2 = conv2d_bn(tower_conv2_1, 96, 3, name=name_fmt.format(branch_idx, 'Conv2d_0c_3x3'))
branch_idx = 3
tower_pool = AveragePooling2D(3, strides=1, padding='same', name=name_fmt.format(branch_idx, 'AvgPool_0a_3x3'))(x)
tower_pool_1 = conv2d_bn(tower_pool, 64, 1, name=name_fmt.format(branch_idx, 'Conv2d_0b_1x1'))
x = layers.concatenate([tower_conv, tower_conv1_1, tower_conv2_2, tower_pool_1],
axis=channel_axis,
name='Mixed_5b')
# 10x block35 (Inception-ResNet-A block): 35 x 35 x 320
for r in range(1, 11):
x = block35(x, name='Block35_{}'.format(r))
# mixed 6a (Reduction-A block): 17 x 17 x 1088
name_fmt = 'Mixed_6a_Branch_{}_{}'
branch_idx = 0
tower_conv = conv2d_bn(x, 384, 3, strides=2, padding='valid', name=name_fmt.format(branch_idx, 'Conv2d_1a_3x3'))
branch_idx = 1
tower_conv1_0 = conv2d_bn(x, 256, 1, name=name_fmt.format(branch_idx, 'Conv2d_0a_1x1'))
tower_conv1_1 = conv2d_bn(tower_conv1_0, 256, 3, name=name_fmt.format(branch_idx, 'Conv2d_0b_3x3'))
tower_conv1_2 = conv2d_bn(tower_conv1_1, 384, 3, strides=2, padding='valid', name=name_fmt.format(branch_idx, 'Conv2d_1a_3x3'))
branch_idx = 2
tower_pool = MaxPooling2D(3, strides=2, padding='valid', name=name_fmt.format(branch_idx, 'MaxPool_1a_3x3'))(x)
x = layers.concatenate([tower_conv, tower_conv1_2, tower_pool],
axis=channel_axis,
name='Mixed_6a')
# 20x block17 (Inception-ResNet-B block): 17 x 17 x 1088
for r in range(1, 21):
x = block17(x, name='Block17_{}'.format(r))
# mixed 7a (Reduction-B block): 8 x 8 x 2080
name_fmt = 'Mixed_7a_Branch_{}_{}'
branch_idx = 0
tower_conv = conv2d_bn(x, 256, 1, name=name_fmt.format(branch_idx, 'Conv2d_0a_1x1'))
tower_conv_1 = conv2d_bn(tower_conv, 384, 3, strides=2, padding='valid', name=name_fmt.format(branch_idx, 'Conv2d_1a_3x3'))
branch_idx = 1
tower_conv1 = conv2d_bn(x, 256, 1, name=name_fmt.format(branch_idx, 'Conv2d_0a_1x1'))
tower_conv1_1 = conv2d_bn(tower_conv1, 288, 3, strides=2, padding='valid', name=name_fmt.format(branch_idx, 'Conv2d_1a_3x3'))
branch_idx = 2
tower_conv2 = conv2d_bn(x, 256, 1, name=name_fmt.format(branch_idx, 'Conv2d_0a_1x1'))
tower_conv2_1 = conv2d_bn(tower_conv2, 288, 3, name=name_fmt.format(branch_idx, 'Conv2d_0b_3x3'))
tower_conv2_2 = conv2d_bn(tower_conv2_1, 320, 3, strides=2, padding='valid', name=name_fmt.format(branch_idx, 'Conv2d_1a_3x3'))
branch_idx = 3
tower_pool = MaxPooling2D(3, strides=2, padding='valid', name=name_fmt.format(branch_idx, 'MaxPool_1a_3x3'))(x)
x = layers.concatenate([tower_conv_1, tower_conv1_1, tower_conv2_2, tower_pool],
axis=channel_axis,
name='Mixed_7a')
# 10x block8 (Inception-ResNet-C block): 8 x 8 x 2080
for r in range(1, 10):
x = block8(x, name='Block8_{}'.format(r))
x = block8(x, scale=1.0, activation=None, name='Block8_10')
# Final convolution block
x = conv2d_bn(x, 1536, 1, name='Conv2d_7b_1x1')
if include_top:
# Classification block
x = GlobalAveragePooling2D(name='AvgPool_1a_8x8')(x)
x = Dropout(1.0 - dropout_keep_prob, name='Dropout')(x)
x = Dense(classes, name='Logits')(x)
x = Activation('softmax', name='Predictions')(x)
else:
if pooling == 'avg':
x = GlobalAveragePooling2D(name='AvgPool')(x)
elif pooling == 'max':
x = GlobalMaxPooling2D(name='MaxPool')(x)
# Ensure that the model takes into account
# any potential predecessors of `input_tensor`.
if input_tensor is not None:
inputs = get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model.
model = Model(inputs, x, name='inception_resnet_v2')
# load weights
if weights == 'imagenet':
if K.image_data_format() == 'channels_first':
if K.backend() == 'tensorflow':
warnings.warn('You are using the TensorFlow backend, yet you '
'are using the Theano '
'image data format convention '
'(`image_data_format="channels_first"`). '
'For best performance, set '
'`image_data_format="channels_last"` in '
'your Keras config '
'at ~/.keras/keras.json.')
if include_top:
weights_path = get_file(
'inception_resnet_v2_weights_tf_dim_ordering_tf_kernels.h5',
WEIGHTS_PATH,
cache_subdir='models',
md5_hash='e693bd0210a403b3192acc6073ad2e96')
else:
weights_path = get_file(
'inception_resnet_v2_weights_tf_dim_ordering_tf_kernels_notop.h5',
WEIGHTS_PATH_NO_TOP,
cache_subdir='models',
md5_hash='d19885ff4a710c122648d3b5c3b684e4')
model.load_weights(weights_path)
return model
def Xception(include_top=True, weights='imagenet',
input_tensor=None, input_shape=None,
pooling=None,
classes=1000):
"""Instantiates the Xception architecture.
Optionally loads weights pre-trained
on ImageNet. This model is available for TensorFlow only,
and can only be used with inputs following the TensorFlow
data format `(width, height, channels)`.
You should set `image_data_format="channels_last"` in your Keras config
located at ~/.keras/keras.json.
Note that the default input image size for this model is 299x299.
# Arguments
include_top: whether to include the fully-connected
layer at the top of the network.
weights: one of `None` (random initialization)
or "imagenet" (pre-training on ImageNet).
input_tensor: optional Keras tensor (i.e. output of `layers.Input()`)
to use as image input for the model.
input_shape: optional shape tuple, only to be specified
if `include_top` is False (otherwise the input shape
has to be `(299, 299, 3)`.
It should have exactly 3 inputs channels,
and width and height should be no smaller than 71.
E.g. `(150, 150, 3)` would be one valid value.
pooling: Optional pooling mode for feature extraction
when `include_top` is `False`.
- `None` means that the output of the model will be
the 4D tensor output of the
last convolutional layer.
- `avg` means that global average pooling
will be applied to the output of the
last convolutional layer, and thus
the output of the model will be a 2D tensor.
- `max` means that global max pooling will
be applied.
classes: optional number of classes to classify images
into, only to be specified if `include_top` is True, and
if no `weights` argument is specified.
# Returns
A Keras model instance.
# Raises
ValueError: in case of invalid argument for `weights`,
or invalid input shape.
RuntimeError: If attempting to run this model with a
backend that does not support separable convolutions.
"""
if weights not in {'imagenet', None}:
raise ValueError('The `weights` argument should be either '
'`None` (random initialization) or `imagenet` '
'(pre-training on ImageNet).')
if weights == 'imagenet' and include_top and classes != 1000:
raise ValueError('If using `weights` as imagenet with `include_top`'
' as true, `classes` should be 1000')
if K.backend() != 'tensorflow':
raise RuntimeError('The Xception model is only available with '
'the TensorFlow backend.')
if K.image_data_format() != 'channels_last':
warnings.warn('The Xception model is only available for the '
'input data format "channels_last" '
'(width, height, channels). '
'However your settings specify the default '
'data format "channels_first" (channels, width, height). '
'You should set `image_data_format="channels_last"` in your Keras '
'config located at ~/.keras/keras.json. '
'The model being returned right now will expect inputs '
'to follow the "channels_last" data format.')
K.set_image_data_format('channels_last')
old_data_format = 'channels_first'
else:
old_data_format = None
# Determine proper input shape
input_shape = _obtain_input_shape(input_shape,
default_size=299,
min_size=71,
data_format=K.image_data_format(),
include_top=include_top)
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
if not K.is_keras_tensor(input_tensor):
img_input = Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
x = Conv2D(32, (3, 3), strides=(2, 2), use_bias=False, name='block1_conv1')(img_input)
x = BatchNormalization(name='block1_conv1_bn')(x)
x = Activation('relu', name='block1_conv1_act')(x)
x = Conv2D(64, (3, 3), use_bias=False, name='block1_conv2')(x)
x = BatchNormalization(name='block1_conv2_bn')(x)
x = Activation('relu', name='block1_conv2_act')(x)
residual = Conv2D(128, (1, 1), strides=(2, 2),
padding='same', use_bias=False)(x)
residual = BatchNormalization()(residual)
x = SeparableConv2D(128, (3, 3), padding='same', use_bias=False, name='block2_sepconv1')(x)
x = BatchNormalization(name='block2_sepconv1_bn')(x)
x = Activation('relu', name='block2_sepconv2_act')(x)
x = SeparableConv2D(128, (3, 3), padding='same', use_bias=False, name='block2_sepconv2')(x)
x = BatchNormalization(name='block2_sepconv2_bn')(x)
x = MaxPooling2D((3, 3), strides=(2, 2), padding='same', name='block2_pool')(x)
x = layers.add([x, residual])
residual = Conv2D(256, (1, 1), strides=(2, 2),
padding='same', use_bias=False)(x)
residual = BatchNormalization()(residual)
x = Activation('relu', name='block3_sepconv1_act')(x)
x = SeparableConv2D(256, (3, 3), padding='same', use_bias=False, name='block3_sepconv1')(x)
x = BatchNormalization(name='block3_sepconv1_bn')(x)
x = Activation('relu', name='block3_sepconv2_act')(x)
x = SeparableConv2D(256, (3, 3), padding='same', use_bias=False, name='block3_sepconv2')(x)
x = BatchNormalization(name='block3_sepconv2_bn')(x)
x = MaxPooling2D((3, 3), strides=(2, 2), padding='same', name='block3_pool')(x)
x = layers.add([x, residual])
residual = Conv2D(728, (1, 1), strides=(2, 2),
padding='same', use_bias=False)(x)
residual = BatchNormalization()(residual)
x = Activation('relu', name='block4_sepconv1_act')(x)
x = SeparableConv2D(728, (3, 3), padding='same', use_bias=False, name='block4_sepconv1')(x)
x = BatchNormalization(name='block4_sepconv1_bn')(x)
x = Activation('relu', name='block4_sepconv2_act')(x)
x = SeparableConv2D(728, (3, 3), padding='same', use_bias=False, name='block4_sepconv2')(x)
x = BatchNormalization(name='block4_sepconv2_bn')(x)
x = MaxPooling2D((3, 3), strides=(2, 2), padding='same', name='block4_pool')(x)
x = layers.add([x, residual])
for i in range(8):
residual = x
prefix = 'block' + str(i + 5)
x = Activation('relu', name=prefix + '_sepconv1_act')(x)
x = SeparableConv2D(728, (3, 3), padding='same', use_bias=False, name=prefix + '_sepconv1')(x)
x = BatchNormalization(name=prefix + '_sepconv1_bn')(x)
x = Activation('relu', name=prefix + '_sepconv2_act')(x)
x = SeparableConv2D(728, (3, 3), padding='same', use_bias=False, name=prefix + '_sepconv2')(x)
x = BatchNormalization(name=prefix + '_sepconv2_bn')(x)
x = Activation('relu', name=prefix + '_sepconv3_act')(x)
x = SeparableConv2D(728, (3, 3), padding='same', use_bias=False, name=prefix + '_sepconv3')(x)
x = BatchNormalization(name=prefix + '_sepconv3_bn')(x)
x = layers.add([x, residual])
residual = Conv2D(1024, (1, 1), strides=(2, 2),
padding='same', use_bias=False)(x)
residual = BatchNormalization()(residual)
x = Activation('relu', name='block13_sepconv1_act')(x)
x = SeparableConv2D(728, (3, 3), padding='same', use_bias=False, name='block13_sepconv1')(x)
x = BatchNormalization(name='block13_sepconv1_bn')(x)
x = Activation('relu', name='block13_sepconv2_act')(x)
x = SeparableConv2D(1024, (3, 3), padding='same', use_bias=False, name='block13_sepconv2')(x)
x = BatchNormalization(name='block13_sepconv2_bn')(x)
x = MaxPooling2D((3, 3), strides=(2, 2), padding='same', name='block13_pool')(x)
x = layers.add([x, residual])
x = SeparableConv2D(1536, (3, 3), padding='same', use_bias=False, name='block14_sepconv1')(x)
x = BatchNormalization(name='block14_sepconv1_bn')(x)
x = Activation('relu', name='block14_sepconv1_act')(x)
x = SeparableConv2D(2048, (3, 3), padding='same', use_bias=False, name='block14_sepconv2')(x)
x = BatchNormalization(name='block14_sepconv2_bn')(x)
x = Activation('relu', name='block14_sepconv2_act')(x)
if include_top:
x = GlobalAveragePooling2D(name='avg_pool')(x)
x = Dense(classes, activation='softmax', name='predictions')(x)
else:
if pooling == 'avg':
x = GlobalAveragePooling2D()(x)
elif pooling == 'max':
x = GlobalMaxPooling2D()(x)
# Ensure that the model takes into account
# any potential predecessors of `input_tensor`.
if input_tensor is not None:
inputs = get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model.
model = Model(inputs, x, name='xception')
# load weights
if weights == 'imagenet':
if include_top:
weights_path = get_file('xception_weights_tf_dim_ordering_tf_kernels.h5',
TF_WEIGHTS_PATH,
cache_subdir='models')
else:
weights_path = get_file('xception_weights_tf_dim_ordering_tf_kernels_notop.h5',
TF_WEIGHTS_PATH_NO_TOP,
cache_subdir='models')
model.load_weights(weights_path)
if old_data_format:
K.set_image_data_format(old_data_format)
return model
def ShuffleNetV2(include_top=True,
input_tensor=None,
scale_factor=1.0,
pooling='max',
input_shape=(224, 224, 3),
load_model=None,
num_shuffle_units=[3, 7, 3],
bottleneck_ratio=1,
classes=1000):
if K.backend() != 'tensorflow':
raise RuntimeError('Only tensorflow supported for now')
name = 'ShuffleNetV2_{}_{}_{}'.format(
scale_factor, bottleneck_ratio,
"".join([str(x) for x in num_shuffle_units]))
out_dim_stage_two = {0.5: 48, 1: 116, 1.5: 176, 2: 244}
if pooling not in ['max', 'avg']:
raise ValueError('Invalid value for pooling')
if not (float(scale_factor) * 4).is_integer():
raise ValueError('Invalid value for scale_factor, should be x over 4')
exp = np.insert(np.arange(len(num_shuffle_units), dtype=np.float32), 0,
0) # [0., 0., 1., 2.]
out_channels_in_stage = 2**exp
out_channels_in_stage *= out_dim_stage_two[
bottleneck_ratio] # calculate output channels for each stage
out_channels_in_stage[0] = 24 # first stage has always 24 output channels
out_channels_in_stage *= scale_factor
out_channels_in_stage = out_channels_in_stage.astype(int)
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
if not K.is_keras_tensor(input_tensor):
img_input = Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
# create shufflenet architecture
x = Conv2D(filters=out_channels_in_stage[0],
kernel_size=(3, 3),
padding='same',
use_bias=False,
strides=(2, 2),
activation='relu',
name='conv1')(img_input)
x = MaxPooling2D(pool_size=(3, 3),
strides=(2, 2),
padding='same',
name='maxpool1')(x)
# create stages containing shufflenet units beginning at stage 2
for stage in range(len(num_shuffle_units)):
repeat = num_shuffle_units[stage]
x = block(x,
out_channels_in_stage,
repeat=repeat,
bottleneck_ratio=bottleneck_ratio,
stage=stage + 2)
if bottleneck_ratio < 2:
k = 1024
else:
k = 2048
x = Conv2D(k,
kernel_size=1,
padding='same',
strides=1,
name='1x1conv5_out',
activation='relu')(x)
if pooling == 'avg':
x = GlobalAveragePooling2D(name='global_avg_pool')(x)
elif pooling == 'max':
x = GlobalMaxPooling2D(name='global_max_pool')(x)
if include_top:
x = Dense(classes, name='fc')(x)
x = Activation('softmax', name='softmax')(x)
if input_tensor:
inputs = get_source_inputs(input_tensor)
else:
inputs = img_input
model = Model(inputs, x, name=name)
if load_model:
model.load_weights('', by_name=True)
return model
def ResNet50(
input_shape,
Dropout,
weights='imagenet',
include_top=True,
input_tensor=None,
#input_shape=None,
pooling=None,
classes=1000,
**kwargs):
"""Instantiates the ResNet50 architecture.
Optionally loads weights pre-trained on ImageNet.
Note that the data format convention used by the model is
the one specified in your Keras config at `~/.keras/keras.json`.
# Arguments
include_top: whether to include the fully-connected
layer at the top of the network.
weights: one of `None` (random initialization),
'imagenet' (pre-training on ImageNet),
or the path to the weights file to be loaded.
input_tensor: optional Keras tensor (i.e. output of `layers.Input()`)
to use as image input for the model.
input_shape: optional shape tuple, only to be specified
if `include_top` is False (otherwise the input shape
has to be `(224, 224, 3)` (with `channels_last` data format)
or `(3, 224, 224)` (with `channels_first` data format).
It should have exactly 3 inputs channels,
and width and height should be no smaller than 32.
E.g. `(200, 200, 3)` would be one valid value.
pooling: Optional pooling mode for feature extraction
when `include_top` is `False`.
- `None` means that the output of the model will be
the 4D tensor output of the
last convolutional block.
- `avg` means that global average pooling
will be applied to the output of the
last convolutional block, and thus
the output of the model will be a 2D tensor.
- `max` means that global max pooling will
be applied.
classes: optional number of classes to classify images
into, only to be specified if `include_top` is True, and
if no `weights` argument is specified.
# Returns
A Keras model instance.
# Raises
ValueError: in case of invalid argument for `weights`,
or invalid input shape.
"""
tf.random.set_random_seed(1)
import random as python_random
python_random.seed(1)
np.random.seed(1)
if not (weights in {'imagenet', None} or os.path.exists(weights)):
raise ValueError('The `weights` argument should be either '
'`None` (random initialization), `imagenet` '
'(pre-training on ImageNet), '
'or the path to the weights file to be loaded.')
if weights == 'imagenet' and include_top and classes != 1000:
raise ValueError(
'If using `weights` as `"imagenet"` with `include_top`'
' as true, `classes` should be 1000')
if input_tensor is None:
img_input = layers.Input(shape=input_shape)
else:
if not backend.is_keras_tensor(input_tensor):
img_input = layers.Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
if backend.image_data_format() == 'channels_last':
bn_axis = 3
else:
bn_axis = 1
x = layers.ZeroPadding2D(padding=(3, 3), name='conv1_pad')(img_input)
x = layers.Conv2D(64, (7, 7),
strides=(2, 2),
padding='valid',
kernel_initializer='he_normal',
name='conv1')(x)
x = layers.BatchNormalization(axis=bn_axis, name='bn_conv1')(x)
x = layers.Activation('relu')(x)
x = layers.ZeroPadding2D(padding=(1, 1), name='pool1_pad')(x)
x = layers.MaxPooling2D((3, 3), strides=(2, 2))(x)
x = conv_block(x, 3, [64, 64, 256], stage=2, block='a', strides=(1, 1))
x = identity_block(x, Dropout, 3, [64, 64, 256], stage=2, block='b')
x = identity_block(x, Dropout, 3, [64, 64, 256], stage=2, block='c')
x = conv_block(x, 3, [128, 128, 512], stage=3, block='a')
x = identity_block(x, Dropout, 3, [128, 128, 512], stage=3, block='b')
x = identity_block(x, Dropout, 3, [128, 128, 512], stage=3, block='c')
x = identity_block(x, Dropout, 3, [128, 128, 512], stage=3, block='d')
x = conv_block(x, 3, [256, 256, 1024], stage=4, block='a')
x = identity_block(x, Dropout, 3, [256, 256, 1024], stage=4, block='b')
x = identity_block(x, Dropout, 3, [256, 256, 1024], stage=4, block='c')
x = identity_block(x, Dropout, 3, [256, 256, 1024], stage=4, block='d')
x = identity_block(x, Dropout, 3, [256, 256, 1024], stage=4, block='e')
x = identity_block(x, Dropout, 3, [256, 256, 1024], stage=4, block='f')
x = conv_block(x, 3, [512, 512, 2048], stage=5, block='a')
x = identity_block(x, Dropout, 3, [512, 512, 2048], stage=5, block='b')
x = identity_block(x, Dropout, 3, [512, 512, 2048], stage=5, block='c')
if include_top:
x = layers.GlobalAveragePooling2D(name='avg_pool')(x)
x = layers.Dense(classes, activation='softmax', name='fc1000')(x)
else:
if pooling == 'avg':
x = layers.GlobalAveragePooling2D()(x)
elif pooling == 'max':
x = layers.GlobalMaxPooling2D()(x)
else:
logging.warning(
'The output shape of `ResNet50(include_top=False)` '
'has been changed since Keras 2.2.0.')
# Ensure that the model takes into account
# any potential predecessors of `input_tensor`.
if input_tensor is not None:
inputs = keras_utils.get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model.
model = models.Model(inputs, x, name='resnet50')
# Load weights.
if weights == 'imagenet':
if include_top:
weights_path = keras_utils.get_file(
'resnet50_weights_tf_dim_ordering_tf_kernels.h5',
WEIGHTS_PATH,
cache_subdir='models',
md5_hash='a7b3fe01876f51b976af0dea6bc144eb')
else:
weights_path = keras_utils.get_file(
'resnet50_weights_tf_dim_ordering_tf_kernels_notop.h5',
WEIGHTS_PATH_NO_TOP,
cache_subdir='models',
md5_hash='a268eb855778b3df3c7506639542a6af')
model.load_weights(weights_path)
if backend.backend() == 'theano':
keras_utils.convert_all_kernels_in_model(model)
elif isinstance(weights, str):
if os.path.isfile(weights):
model.load_weights(weights)
for layer, pre in zip(model.layers, weights):
weights = layer.get_weights()
if weights:
if np.array_equal(weights[0], pre[0]):
logging.info('not loaded %s' % layer.name)
else:
logging.info('loaded %s' % layer.name)
return model
def nn_base(input_tensor=None, trainable=False):
# Determine proper input shape
if K.image_dim_ordering() == 'th':
input_shape = (3, None, None)
else:
input_shape = (None, None, 3)
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
if not K.is_keras_tensor(input_tensor):
img_input = Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
if K.image_dim_ordering() == 'tf':
bn_axis = 3
else:
bn_axis = 1
# Stem block: 35 x 35 x 192
x = conv2d_bn(img_input, 32, 3, strides=2, padding='valid', name='Stem_block' + '_conv1')
x = conv2d_bn(x, 32, 3, padding='valid', name='Stem_block' + '_conv2')
x = conv2d_bn(x, 64, 3, name='Stem_block' + '_conv3')
x = MaxPooling2D(3, strides=2)(x)
x = conv2d_bn(x, 80, 1, padding='valid', name='Stem_block' + '_conv4')
x = conv2d_bn(x, 192, 3, padding='valid', name='Stem_block' + '_conv5')
x = MaxPooling2D(3, strides=2)(x)
# Mixed 5b (Inception-A block): 35 x 35 x 320
branch_0 = conv2d_bn(x, 96, 1, name='Inception_A_block' + '_conv1')
branch_1 = conv2d_bn(x, 48, 1, name='Inception_A_block' + '_conv2')
branch_1 = conv2d_bn(branch_1, 64, 5, name='Inception_A_block' + '_conv3')
branch_2 = conv2d_bn(x, 64, 1, name='Inception_A_block' + '_conv4')
branch_2 = conv2d_bn(branch_2, 96, 3, name='Inception_A_block' + '_conv5')
branch_2 = conv2d_bn(branch_2, 96, 3, name='Inception_A_block' + '_conv6')
branch_pool = AveragePooling2D(3, strides=1, padding='same')(x)
branch_pool = conv2d_bn(branch_pool, 64, 1, name='Inception_A_block' + '_conv7')
branches = [branch_0, branch_1, branch_2, branch_pool]
channel_axis = 1 if K.image_data_format() == 'channels_first' else 3
x = Concatenate(axis=channel_axis, name='mixed_5b')(branches)
# 10x block35 (Inception-ResNet-A block): 35 x 35 x 320
for block_idx in range(1, 11):
x = inception_resnet_block(x,
scale=0.17,
block_type='block35',
block_idx=block_idx)
# Mixed 6a (Reduction-A block): 17 x 17 x 1088
branch_0 = conv2d_bn(x, 384, 3, strides=2, padding='valid', name='Reduction_A_block' + '_conv1')
branch_1 = conv2d_bn(x, 256, 1, name='Reduction_A_block' + '_conv2')
branch_1 = conv2d_bn(branch_1, 256, 3, name='Reduction_A_block' + '_conv3')
branch_1 = conv2d_bn(branch_1, 384, 3, strides=2, padding='valid', name='Reduction_A_block' + '_conv4')
branch_pool = MaxPooling2D(3, strides=2, padding='valid')(x)
branches = [branch_0, branch_1, branch_pool]
x = Concatenate(axis=channel_axis, name='mixed_6a')(branches)
# 20x block17 (Inception-ResNet-B block): 17 x 17 x 1088
for block_idx in range(1, 21):
x = inception_resnet_block(x,
scale=0.1,
block_type='block17',
block_idx=block_idx)
return x
def nn_base(input_tensor=None, trainable=False):
# Determine proper input shape
if K.image_dim_ordering() == 'th':
input_shape = (3, None, None)
else:
input_shape = (None, None, 3)
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
if not K.is_keras_tensor(input_tensor):
img_input = Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
if K.image_dim_ordering() == 'tf':
bn_axis = 3
else:
bn_axis = 1
x = ZeroPadding2D((3, 3))(img_input)
x = Convolution2D(64, (7, 7),
strides=(2, 2),
name='conv1',
trainable=trainable)(x)
x = BatchNormalization(axis=bn_axis, name='bn_conv1')(x)
x = Activation('relu')(x)
x = MaxPooling2D((3, 3), strides=(2, 2))(x)
x = conv_block(x,
3, [64, 64, 256],
stage=2,
block='a',
strides=(1, 1),
trainable=trainable)
x = identity_block(x,
3, [64, 64, 256],
stage=2,
block='b',
trainable=trainable)
x = identity_block(x,
3, [64, 64, 256],
stage=2,
block='c',
trainable=trainable)
x = conv_block(x,
3, [128, 128, 512],
stage=3,
block='a',
trainable=trainable)
x = identity_block(x,
3, [128, 128, 512],
stage=3,
block='b',
trainable=trainable)
x = identity_block(x,
3, [128, 128, 512],
stage=3,
block='c',
trainable=trainable)
x = identity_block(x,
3, [128, 128, 512],
stage=3,
block='d',
trainable=trainable)
x = conv_block(x,
3, [256, 256, 1024],
stage=4,
block='a',
trainable=trainable)
x = identity_block(x,
3, [256, 256, 1024],
stage=4,
block='b',
trainable=trainable)
x = identity_block(x,
3, [256, 256, 1024],
stage=4,
block='c',
trainable=trainable)
x = identity_block(x,
3, [256, 256, 1024],
stage=4,
block='d',
trainable=trainable)
x = identity_block(x,
3, [256, 256, 1024],
stage=4,
block='e',
trainable=trainable)
x = identity_block(x,
3, [256, 256, 1024],
stage=4,
block='f',
trainable=trainable)
return x
def nn_base(input_tensor=None, trainable=False):
if K.image_dim_ordering() == 'th':
input_shape = (3, None, None)
else:
input_shape = (None, None, 3)
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
if not K.is_keras_tensor(input_tensor):
img_input = Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
if K.image_dim_ordering() == 'tf':
bn_axis = 3 # channels
else:
bn_axis = 1
# Start VGG16
#Block 1
x = Conv2D(64, (3, 3), activation='relu', padding='same',
name='conv1_1')(img_input)
x = Conv2D(64, (3, 3), activation='relu', padding='same',
name='conv1_2')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name="pool1_1")(x)
# Block 2
x = Conv2D(128, (3, 3), activation='relu', padding='same',
name='conv2_1')(x)
x = Conv2D(128, (3, 3), activation='relu', padding='same',
name='conv2_2')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name="pool2_1")(x)
# Block 3
x = Conv2D(256, (3, 3), activation='relu', padding='same',
name='conv3_1')(x)
x = Conv2D(256, (3, 3), activation='relu', padding='same',
name='conv3_2')(x)
x = Conv2D(256, (3, 3), activation='relu', padding='same',
name='conv3_3')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name="pool3_1")(x)
# Block 4
x = Conv2D(512, (3, 3), activation='relu', padding='same',
name='conv4_1')(x)
x = Conv2D(512, (3, 3), activation='relu', padding='same',
name='conv4_2')(x)
x = Conv2D(512, (3, 3), activation='relu', padding='same',
name='conv4_3')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name="pool4_1")(x)
# Block 5
x = Conv2D(512, (3, 3), activation='relu', padding='same',
name='conv5_1')(x)
x = Conv2D(512, (3, 3), activation='relu', padding='same',
name='conv5_2')(x)
x = Conv2D(512, (3, 3), activation='relu', padding='same',
name='conv5_3')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name="pool4_1")(x)
# Without classification block
return x
def DenseNetFCN(input_shape,
nb_dense_block=5,
growth_rate=16,
nb_layers_per_block=4,
reduction=0.0,
dropout_rate=0.0,
weight_decay=1E-4,
init_conv_filters=48,
include_top=True,
weights=None,
input_tensor=None,
classes=1,
activation='softmax',
upsampling_conv=128,
upsampling_type='upsampling',
batchsize=None):
"""Instantiate the DenseNet FCN architecture.
Note that when using TensorFlow,
for best performance you should set
`image_dim_ordering="tf"` in your Keras config
at ~/.keras/keras.json.
# Arguments
nb_dense_block: number of dense blocks to add to end (generally = 3)
growth_rate: number of filters to add per dense block
nb_layers_per_block: number of layers in each dense block.
Can be a positive integer or a list.
If positive integer, a set number of layers per dense block.
If list, nb_layer is used as provided. Note that list size must
be (nb_dense_block + 1)
reduction: reduction factor of transition blocks.
Note : reduction value is inverted to compute compression.
dropout_rate: dropout rate
weight_decay: weight decay factor
init_conv_filters: number of layers in the initial convolution layer
include_top: whether to include the fully-connected
layer at the top of the network.
weights: one of `None` (random initialization) or
"cifar10" (pre-training on CIFAR-10)..
input_tensor: optional Keras tensor (i.e. output of `layers.Input()`)
to use as image input for the model.
input_shape: optional shape tuple, only to be specified
if `include_top` is False (otherwise the input shape
has to be `(32, 32, 3)` (with `tf` dim ordering)
or `(3, 32, 32)` (with `th` dim ordering).
Width and height should be no smaller than 8.
E.g. `(200, 200, 3)` would be one valid value.
classes: optional number of classes to classify images
into, only to be specified if `include_top` is True, and
if no `weights` argument is specified.
activation: Type of activation at the top layer. Can be one of 'softmax' or 'sigmoid'.
Note that if sigmoid is used, classes must be 1.
upsampling_conv: number of convolutional layers in upsampling via subpixel convolution
upsampling_type: Can be one of 'upsampling', 'deconv', 'atrous' and
'subpixel'. Defines type of upsampling algorithm used.
batchsize: Fixed batch size. This is a temporary requirement for
computation of output shape in the case of Deconvolution2D layers.
Parameter will be removed in next iteration of Keras, which infers
output shape of deconvolution layers automatically.
# Returns
A Keras model instance.
"""
if weights not in {None}:
raise ValueError('The `weights` argument should be '
'`None` (random initialization) as no '
'model weights are provided.')
upsampling_type = upsampling_type.lower()
if upsampling_type not in ['upsampling', 'deconv', 'atrous', 'subpixel']:
raise ValueError(
'Parameter "upsampling_type" must be one of "upsampling", '
'"deconv", "atrous" or "subpixel".')
if upsampling_type == 'deconv' and batchsize is None:
raise ValueError(
'If "upsampling_type" is deconvoloution, then a fixed '
'batch size must be provided in batchsize parameter.')
if input_shape is None:
raise ValueError(
'For fully convolutional models, input shape must be supplied.')
if type(nb_layers_per_block) is not list and nb_dense_block < 1:
raise ValueError(
'Number of dense layers per block must be greater than 1. Argument '
'value was %d.' % (nb_layers_per_block))
if upsampling_type == 'atrous':
warnings.warn(
'Atrous Convolution upsampling does not correctly work (see https://github.com/fchollet/keras/issues/4018).\n'
'Switching to `upsampling` type upscaling.')
upsampling_type = 'upsampling'
if activation not in ['softmax', 'sigmoid']:
raise ValueError('activation must be one of "softmax" or "sigmoid"')
if activation == 'sigmoid' and classes != 1:
raise ValueError(
'sigmoid activation can only be used when classes = 1')
# Determine proper input shape
min_size = 2**nb_dense_block
if K.image_dim_ordering() == 'th':
if input_shape is not None:
if ((input_shape[1] is not None and input_shape[1] < min_size) or
(input_shape[2] is not None and input_shape[2] < min_size)):
raise ValueError('Input size must be at least ' +
str(min_size) + 'x' + str(min_size) + ', got '
'`input_shape=' + str(input_shape) + '`')
else:
input_shape = (classes, None, None)
else:
if input_shape is not None:
if ((input_shape[0] is not None and input_shape[0] < min_size) or
(input_shape[1] is not None and input_shape[1] < min_size)):
raise ValueError('Input size must be at least ' +
str(min_size) + 'x' + str(min_size) + ', got '
'`input_shape=' + str(input_shape) + '`')
else:
input_shape = (None, None, classes)
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
if not K.is_keras_tensor(input_tensor):
img_input = Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
x = __create_fcn_dense_net(classes, img_input, include_top, nb_dense_block,
growth_rate, reduction, dropout_rate,
weight_decay, nb_layers_per_block,
upsampling_conv, upsampling_type, batchsize,
init_conv_filters, input_shape)
# Ensure that the model takes into account
# any potential predecessors of `input_tensor`.
#if input_tensor is not None:
# inputs = get_source_inputs(input_tensor)
#else:
# inputs = img_input
## Create model.
#model = Model(inputs, x, name='fcn-densenet')
#
return x
def nn_base(input_tensor=None, trainable=False):
# Determine proper input shape
if K.image_dim_ordering() == 'th':
input_shape = (3, None, None)
else:
input_shape = (None, None, 3)
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
if not K.is_keras_tensor(input_tensor):
img_input = Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
if K.image_dim_ordering() == 'tf':
bn_axis = 3
else:
bn_axis = 1
# Block 1
x = Conv2D(64, (3, 3),
activation='relu',
padding='same',
name='block1_conv1')(img_input)
x = Conv2D(64, (3, 3),
activation='relu',
padding='same',
name='block1_conv2')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='block1_pool')(x)
# Block 2
x = Conv2D(128, (3, 3),
activation='relu',
padding='same',
name='block2_conv1')(x)
x = Conv2D(128, (3, 3),
activation='relu',
padding='same',
name='block2_conv2')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='block2_pool')(x)
# Block 3
x = Conv2D(256, (3, 3),
activation='relu',
padding='same',
name='block3_conv1')(x)
x = Conv2D(256, (3, 3),
activation='relu',
padding='same',
name='block3_conv2')(x)
x = Conv2D(256, (3, 3),
activation='relu',
padding='same',
name='block3_conv3')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='block3_pool')(x)
# Block 4
x = Conv2D(512, (3, 3),
activation='relu',
padding='same',
name='block4_conv1')(x)
x = Conv2D(512, (3, 3),
activation='relu',
padding='same',
name='block4_conv2')(x)
x = Conv2D(512, (3, 3),
activation='relu',
padding='same',
name='block4_conv3')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='block4_pool')(x)
return x
def fmeasure(y_true, y_pred):
try:
_ = K.is_keras_tensor(y_pred)
return fbeta_score_K(y_true, y_pred, beta=1)
except ValueError:
return fbeta_score_np(y_true, y_pred, beta=1)
def VGG16_Avg(include_top=True,
weights='imagenet',
input_tensor=None,
input_shape=None,
classes=1000):
if weights not in {'imagenet', None}:
raise ValueError('The `weights` argument should be either '
'`None` (random initialization) or `imagenet` '
'(pre-training on ImageNet).')
if weights == 'imagenet' and include_top and classes != 1000:
raise ValueError('If using `weights` as imagenet with `include_top`'
' as true, `classes` should be 1000')
# Determine proper input shape
input_shape = _obtain_input_shape(input_shape,
default_size=224,
min_size=48,
data_format=K.image_data_format(),
include_top=include_top)
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
if not K.is_keras_tensor(input_tensor):
img_input = Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
# Block 1
x = Convolution2D(64,
3,
3,
activation='relu',
border_mode='same',
name='block1_conv1')(img_input)
x = Convolution2D(64,
3,
3,
activation='relu',
border_mode='same',
name='block1_conv2')(x)
x = AveragePooling2D((2, 2), strides=(2, 2), name='block1_pool')(x)
# Block 2
x = Convolution2D(128,
3,
3,
activation='relu',
border_mode='same',
name='block2_conv1')(x)
x = Convolution2D(128,
3,
3,
activation='relu',
border_mode='same',
name='block2_conv2')(x)
x = AveragePooling2D((2, 2), strides=(2, 2), name='block2_pool')(x)
# Block 3
x = Convolution2D(256,
3,
3,
activation='relu',
border_mode='same',
name='block3_conv1')(x)
x = Convolution2D(256,
3,
3,
activation='relu',
border_mode='same',
name='block3_conv2')(x)
x = Convolution2D(256,
3,
3,
activation='relu',
border_mode='same',
name='block3_conv3')(x)
x = AveragePooling2D((2, 2), strides=(2, 2), name='block3_pool')(x)
# Block 4
x = Convolution2D(512,
3,
3,
activation='relu',
border_mode='same',
name='block4_conv1')(x)
x = Convolution2D(512,
3,
3,
activation='relu',
border_mode='same',
name='block4_conv2')(x)
x = Convolution2D(512,
3,
3,
activation='relu',
border_mode='same',
name='block4_conv3')(x)
x = AveragePooling2D((2, 2), strides=(2, 2), name='block4_pool')(x)
# Block 5
x = Convolution2D(512,
3,
3,
activation='relu',
border_mode='same',
name='block5_conv1')(x)
x = Convolution2D(512,
3,
3,
activation='relu',
border_mode='same',
name='block5_conv2')(x)
x = Convolution2D(512,
3,
3,
activation='relu',
border_mode='same',
name='block5_conv3')(x)
x = AveragePooling2D((2, 2), strides=(2, 2), name='block5_pool')(x)
if include_top:
# Classification block
x = Flatten(name='flatten')(x)
x = Dense(4096, activation='relu', name='fc1')(x)
x = Dense(4096, activation='relu', name='fc2')(x)
x = Dense(classes, activation='softmax', name='predictions')(x)
# Ensure that the model takes into account
# any potential predecessors of `input_tensor`.
if input_tensor is not None:
inputs = get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model.
model = Model(inputs, x, name='vgg16')
# load weights
if weights == 'imagenet':
if K.image_dim_ordering() == 'th':
if include_top:
weights_path = get_file(
'vgg16_weights_th_dim_ordering_th_kernels.h5',
TH_WEIGHTS_PATH,
cache_subdir='models')
else:
weights_path = get_file(
'vgg16_weights_th_dim_ordering_th_kernels_notop.h5',
TH_WEIGHTS_PATH_NO_TOP,
cache_subdir='models')
model.load_weights(weights_path)
if K.backend() == 'tensorflow':
warnings.warn('You are using the TensorFlow backend, yet you '
'are using the Theano '
'image dimension ordering convention '
'(`image_dim_ordering="th"`). '
'For best performance, set '
'`image_dim_ordering="tf"` in '
'your Keras config '
'at ~/.keras/keras.json.')
convert_all_kernels_in_model(model)
else:
if include_top:
weights_path = get_file(
'vgg16_weights_tf_dim_ordering_tf_kernels.h5',
TF_WEIGHTS_PATH,
cache_subdir='models')
else:
weights_path = get_file(
'vgg16_weights_tf_dim_ordering_tf_kernels_notop.h5',
TF_WEIGHTS_PATH_NO_TOP,
cache_subdir='models')
model.load_weights(weights_path)
if K.backend() == 'theano':
convert_all_kernels_in_model(model)
return model
def VGG16_Avg(include_top=True, weights='imagenet', input_tensor=None, input_shape=None, classes=1000):
if weights not in {'imagenet', None}:
raise ValueError('The `weights` argument should be either '
'`None` (random initialization) or `imagenet` '
'(pre-training on ImageNet).')
if weights == 'imagenet' and include_top and classes != 1000:
raise ValueError('If using `weights` as imagenet with `include_top`'
' as true, `classes` should be 1000')
# Determine proper input shape
input_shape = _obtain_input_shape(input_shape,
default_size=224,
min_size=48,
dim_ordering=K.image_dim_ordering(),
include_top=include_top)
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
if not K.is_keras_tensor(input_tensor):
img_input = Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
# Block 1
x = Convolution2D(64, 3, 3, activation='relu', border_mode='same', name='block1_conv1')(img_input)
x = Convolution2D(64, 3, 3, activation='relu', border_mode='same', name='block1_conv2')(x)
x = AveragePooling2D((2, 2), strides=(2, 2), name='block1_pool')(x)
# Block 2
x = Convolution2D(128, 3, 3, activation='relu', border_mode='same', name='block2_conv1')(x)
x = Convolution2D(128, 3, 3, activation='relu', border_mode='same', name='block2_conv2')(x)
x = AveragePooling2D((2, 2), strides=(2, 2), name='block2_pool')(x)
# Block 3
x = Convolution2D(256, 3, 3, activation='relu', border_mode='same', name='block3_conv1')(x)
x = Convolution2D(256, 3, 3, activation='relu', border_mode='same', name='block3_conv2')(x)
x = Convolution2D(256, 3, 3, activation='relu', border_mode='same', name='block3_conv3')(x)
x = AveragePooling2D((2, 2), strides=(2, 2), name='block3_pool')(x)
# Block 4
x = Convolution2D(512, 3, 3, activation='relu', border_mode='same', name='block4_conv1')(x)
x = Convolution2D(512, 3, 3, activation='relu', border_mode='same', name='block4_conv2')(x)
x = Convolution2D(512, 3, 3, activation='relu', border_mode='same', name='block4_conv3')(x)
x = AveragePooling2D((2, 2), strides=(2, 2), name='block4_pool')(x)
# Block 5
x = Convolution2D(512, 3, 3, activation='relu', border_mode='same', name='block5_conv1')(x)
x = Convolution2D(512, 3, 3, activation='relu', border_mode='same', name='block5_conv2')(x)
x = Convolution2D(512, 3, 3, activation='relu', border_mode='same', name='block5_conv3')(x)
x = AveragePooling2D((2, 2), strides=(2, 2), name='block5_pool')(x)
if include_top:
# Classification block
x = Flatten(name='flatten')(x)
x = Dense(4096, activation='relu', name='fc1')(x)
x = Dense(4096, activation='relu', name='fc2')(x)
x = Dense(classes, activation='softmax', name='predictions')(x)
# Ensure that the model takes into account
# any potential predecessors of `input_tensor`.
if input_tensor is not None:
inputs = get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model.
model = Model(inputs, x, name='vgg16')
# load weights
if weights == 'imagenet':
if K.image_dim_ordering() == 'th':
if include_top:
weights_path = get_file('vgg16_weights_th_dim_ordering_th_kernels.h5',
TH_WEIGHTS_PATH,
cache_subdir='models')
else:
weights_path = get_file('vgg16_weights_th_dim_ordering_th_kernels_notop.h5',
TH_WEIGHTS_PATH_NO_TOP,
cache_subdir='models')
model.load_weights(weights_path)
if K.backend() == 'tensorflow':
warnings.warn('You are using the TensorFlow backend, yet you '
'are using the Theano '
'image dimension ordering convention '
'(`image_dim_ordering="th"`). '
'For best performance, set '
'`image_dim_ordering="tf"` in '
'your Keras config '
'at ~/.keras/keras.json.')
convert_all_kernels_in_model(model)
else:
if include_top:
weights_path = get_file('vgg16_weights_tf_dim_ordering_tf_kernels.h5',
TF_WEIGHTS_PATH,
cache_subdir='models')
else:
weights_path = get_file('vgg16_weights_tf_dim_ordering_tf_kernels_notop.h5',
TF_WEIGHTS_PATH_NO_TOP,
cache_subdir='models')
model.load_weights(weights_path)
if K.backend() == 'theano':
convert_all_kernels_in_model(model)
return model
def ResNet(stack_fn,
preact,
use_bias,
model_name='resnet',
include_top=True,
weights='imagenet',
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000,
**kwargs):
"""Instantiates the ResNet, ResNetV2, and ResNeXt architecture.
Optionally loads weights pre-trained on ImageNet.
Note that the data format convention used by the model is
the one specified in your Keras config at `~/.keras/keras.json`.
# Arguments
stack_fn: a function that returns output tensor for the
stacked residual blocks.
preact: whether to use pre-activation or not
(True for ResNetV2, False for ResNet and ResNeXt).
use_bias: whether to use biases for convolutional layers or not
(True for ResNet and ResNetV2, False for ResNeXt).
model_name: string, model name.
include_top: whether to include the fully-connected
layer at the top of the network.
weights: one of `None` (random initialization),
'imagenet' (pre-training on ImageNet),
or the path to the weights file to be loaded.
input_tensor: optional Keras tensor
(i.e. output of `Input()`)
to use as image input for the model.
input_shape: optional shape tuple, only to be specified
if `include_top` is False (otherwise the input shape
has to be `(224, 224, 3)` (with `channels_last` data format)
or `(3, 224, 224)` (with `channels_first` data format).
It should have exactly 3 inputs channels.
pooling: optional pooling mode for feature extraction
when `include_top` is `False`.
- `None` means that the output of the model will be
the 4D tensor output of the
last convolutional layer.
- `avg` means that global average pooling
will be applied to the output of the
last convolutional layer, and thus
the output of the model will be a 2D tensor.
- `max` means that global max pooling will
be applied.
classes: optional number of classes to classify images
into, only to be specified if `include_top` is True, and
if no `weights` argument is specified.
# Returns
A Keras model instance.
# Raises
ValueError: in case of invalid argument for `weights`,
or invalid input shape.
"""
#global backend, layers, models, keras_utils
#backend, layers, models, keras_utils = get_submodules_from_kwargs(kwargs)
if not (weights in {'imagenet', None} or os.path.exists(weights)):
raise ValueError('The `weights` argument should be either '
'`None` (random initialization), `imagenet` '
'(pre-training on ImageNet), '
'or the path to the weights file to be loaded.')
if weights == 'imagenet' and include_top and classes != 1000:
raise ValueError(
'If using `weights` as `"imagenet"` with `include_top`'
' as true, `classes` should be 1000')
# Determine proper input shape
#input_shape = _obtain_input_shape(input_shape,
# default_size=224,
# min_size=32,
#data_format=backend.image_data_format(),
# require_flatten=include_top,
# weights=weights)
input_shape = (64, 64, 3)
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
if not backend.is_keras_tensor(input_tensor):
img_input = Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
bn_axis = 3 if backend.image_data_format() == 'channels_last' else 1
x = ZeroPadding2D(padding=((3, 3), (3, 3)), name='conv1_pad')(img_input)
x = Conv2D(64, 7, strides=2, use_bias=use_bias, name='conv1_conv')(x)
if preact is False:
x = BatchNormalization(axis=bn_axis, epsilon=1.001e-5,
name='conv1_bn')(x)
x = Activation('relu', name='conv1_relu')(x)
x = ZeroPadding2D(padding=((1, 1), (1, 1)), name='pool1_pad')(x)
x = MaxPooling2D(3, strides=2, name='pool1_pool')(x)
x = stack_fn(x)
if preact is True:
x = BatchNormalization(axis=bn_axis, epsilon=1.001e-5,
name='post_bn')(x)
x = Activation('relu', name='post_relu')(x)
if include_top:
x = GlobalAveragePooling2D(name='avg_pool')(x)
x = Dense(classes, activation='softmax', name='probs')(x)
else:
if pooling == 'avg':
x = GlobalAveragePooling2D(name='avg_pool')(x)
elif pooling == 'max':
x = GlobalMaxPooling2D(name='max_pool')(x)
# Ensure that the model takes into account
# any potential predecessors of `input_tensor`.
if input_tensor is not None:
inputs = keras_utils.get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model.
model = Model(inputs, x, name=model_name)
# Load weights.
if (weights == 'imagenet') and (model_name in WEIGHTS_HASHES):
if include_top:
file_name = model_name + '_weights_tf_dim_ordering_tf_kernels.h5'
file_hash = WEIGHTS_HASHES[model_name][0]
else:
file_name = model_name + '_weights_tf_dim_ordering_tf_kernels_notop.h5'
file_hash = WEIGHTS_HASHES[model_name][1]
weights_path = keras_utils.get_file(file_name,
BASE_WEIGHTS_PATH + file_name,
cache_subdir='models',
file_hash=file_hash)
model.load_weights(weights_path)
elif weights is not None:
model.load_weights(weights)
return model
def DenseNet(input_shape=None,
depth=40,
nb_dense_block=3,
growth_rate=12,
nb_filter=-1,
nb_layers_per_block=-1,
bottleneck=False,
reduction=0.0,
dropout_rate=0.0,
weight_decay=1e-4,
subsample_initial_block=False,
include_top=True,
weights=None,
input_tensor=None,
pooling=None,
classes=10,
activation='softmax',
transition_pooling='avg'):
'''Instantiate the DenseNet architecture.
The model and the weights are compatible with both
TensorFlow and Theano. The dimension ordering
convention used by the model is the one
specified in your Keras config file.
# Arguments
input_shape: optional shape tuple, only to be specified
if `include_top` is False (otherwise the input shape
has to be `(224, 224, 3)` (with `channels_last` dim ordering)
or `(3, 224, 224)` (with `channels_first` dim ordering).
It should have exactly 3 inputs channels,
and width and height should be no smaller than 8.
E.g. `(224, 224, 3)` would be one valid value.
depth: number or layers in the DenseNet
nb_dense_block: number of dense blocks to add to end
growth_rate: number of filters to add per dense block
nb_filter: initial number of filters. -1 indicates initial
number of filters will default to 2 * growth_rate
nb_layers_per_block: number of layers in each dense block.
Can be a -1, positive integer or a list.
If -1, calculates nb_layer_per_block from the network depth.
If positive integer, a set number of layers per dense block.
If list, nb_layer is used as provided. Note that list size must
be nb_dense_block
bottleneck: flag to add bottleneck blocks in between dense blocks
reduction: reduction factor of transition blocks.
Note : reduction value is inverted to compute compression.
dropout_rate: dropout rate
weight_decay: weight decay rate
subsample_initial_block: Changes model type to suit different datasets.
Should be set to True for ImageNet, and False for CIFAR datasets.
When set to True, the initial convolution will be strided and
adds a MaxPooling2D before the initial dense block.
include_top: whether to include the fully-connected
layer at the top of the network.
weights: one of `None` (random initialization) or
'imagenet' (pre-training on ImageNet)..
input_tensor: optional Keras tensor (i.e. output of `layers.Input()`)
to use as image input for the model.
pooling: Optional pooling mode for feature extraction
when `include_top` is `False`.
- `None` means that the output of the model
will be the 4D tensor output of the
last convolutional layer.
- `avg` means that global average pooling
will be applied to the output of the
last convolutional layer, and thus
the output of the model will be a
2D tensor.
- `max` means that global max pooling will
be applied.
classes: optional number of classes to classify images
into, only to be specified if `include_top` is True, and
if no `weights` argument is specified.
activation: Type of activation at the top layer. Can be one of
'softmax' or 'sigmoid'. Note that if sigmoid is used,
classes must be 1.
transition_pooling: `avg` for avg pooling (default), `max` for max pooling,
None for no pooling during scale transition blocks. Please note that this
default differs from the DenseNetFCN paper in accordance with the DenseNet
paper.
# Returns
A Keras model instance.
# Raises
ValueError: in case of invalid argument for `weights`,
or invalid input shape.
'''
if weights not in {'imagenet', None}:
raise ValueError('The `weights` argument should be either '
'`None` (random initialization) or `imagenet` '
'(pre-training on ImageNet).')
if weights == 'imagenet' and include_top and classes != 1000:
raise ValueError('If using `weights` as ImageNet with `include_top` '
'as true, `classes` should be 1000')
if activation not in ['softmax', 'sigmoid']:
raise ValueError('activation must be one of "softmax" or "sigmoid"')
if activation == 'sigmoid' and classes != 1:
raise ValueError('sigmoid activation can only be used when classes = 1')
# Determine proper input shape
input_shape = _obtain_input_shape(input_shape,
default_size=32,
min_size=8,
data_format=K.image_data_format(),
require_flatten=include_top)
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
if not K.is_keras_tensor(input_tensor):
img_input = Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
x = __create_dense_net(classes, img_input, include_top, depth, nb_dense_block,
growth_rate, nb_filter, nb_layers_per_block, bottleneck,
reduction, dropout_rate, weight_decay, subsample_initial_block,
pooling, activation, transition_pooling)
# Ensure that the model takes into account
# any potential predecessors of `input_tensor`.
if input_tensor is not None:
inputs = get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model.
model = Model(inputs, x, name='densenet')
# load weights
if weights == 'imagenet':
weights_loaded = False
if (depth == 121) and (nb_dense_block == 4) and (growth_rate == 32) and (nb_filter == 64) and \
(bottleneck is True) and (reduction == 0.5) and (subsample_initial_block):
if include_top:
weights_path = get_file('DenseNet-BC-121-32.h5',
DENSENET_121_WEIGHTS_PATH,
cache_subdir='models',
md5_hash='a439dd41aa672aef6daba4ee1fd54abd')
else:
weights_path = get_file('DenseNet-BC-121-32-no-top.h5',
DENSENET_121_WEIGHTS_PATH_NO_TOP,
cache_subdir='models',
md5_hash='55e62a6358af8a0af0eedf399b5aea99')
model.load_weights(weights_path, by_name=True)
weights_loaded = True
if (depth == 161) and (nb_dense_block == 4) and (growth_rate == 48) and (nb_filter == 96) and \
(bottleneck is True) and (reduction == 0.5) and (subsample_initial_block):
if include_top:
weights_path = get_file('DenseNet-BC-161-48.h5',
DENSENET_161_WEIGHTS_PATH,
cache_subdir='models',
md5_hash='6c326cf4fbdb57d31eff04333a23fcca')
else:
weights_path = get_file('DenseNet-BC-161-48-no-top.h5',
DENSENET_161_WEIGHTS_PATH_NO_TOP,
cache_subdir='models',
md5_hash='1a9476b79f6b7673acaa2769e6427b92')
model.load_weights(weights_path, by_name=True)
weights_loaded = True
if (depth == 169) and (nb_dense_block == 4) and (growth_rate == 32) and (nb_filter == 64) and \
(bottleneck is True) and (reduction == 0.5) and (subsample_initial_block):
if include_top:
weights_path = get_file('DenseNet-BC-169-32.h5',
DENSENET_169_WEIGHTS_PATH,
cache_subdir='models',
md5_hash='914869c361303d2e39dec640b4e606a6')
else:
weights_path = get_file('DenseNet-BC-169-32-no-top.h5',
DENSENET_169_WEIGHTS_PATH_NO_TOP,
cache_subdir='models',
md5_hash='89c19e8276cfd10585d5fadc1df6859e')
model.load_weights(weights_path, by_name=True)
weights_loaded = True
if weights_loaded:
if K.backend() == 'theano':
convert_all_kernels_in_model(model)
if K.image_data_format() == 'channels_first' and K.backend() == 'tensorflow':
warnings.warn('You are using the TensorFlow backend, yet you '
'are using the Theano '
'image data format convention '
'(`image_data_format="channels_first"`). '
'For best performance, set '
'`image_data_format="channels_last"` in '
'your Keras config '
'at ~/.keras/keras.json.')
print("Weights for the model were loaded successfully")
return model
def SmallResNet(n=9,
filters=[16, 32, 64],
include_top=True,
weights=None,
input_tensor=None,
input_shape=None,
pooling='avg',
regularizer=regularizers.l2(0.0002),
activation='relu',
top_activation='softmax',
conv_shortcut=False,
bn=True,
classes=100,
name=None):
"""Instantiates the CIFAR ResNet architecture described in section 4.2 of the paper.
# Arguments
n: number of blocks in each unit
filters: list of number of filters in each unit
include_top: whether to include the fully-connected
layer at the top of the network.
weights: `None` (random initialization)
or path to weights file.
input_tensor: optional Keras tensor (i.e. output of `layers.Input()`)
to use as image input for the model.
input_shape: optional shape tuple, only to be specified
if `include_top` is False (otherwise the input shape
has to be `(32, 32, 3)` (with `channels_last` data format)
or `(3, 32, 32)` (with `channels_first` data format).
It should have exactly 3 inputs channels.
pooling: Optional pooling mode for feature extraction
when `include_top` is `False`.
- `avg` means that global average pooling
will be applied to the output of the
last convolutional layer, and thus
the output of the model will be a 2D tensor.
- `max` means that global max pooling will
be applied.
regularizer: weight of kernel regularizer.
activation: name of the activation function to be used.
top_activation: name of the activation function to be used for the top layer.
conv_shortcut: boolean, specifying whether to use padding (False) or
convolution (True) at the shortcuts.
bn: boolean specifying whether to include BatchNormalization layers.
classes: optional number of classes to classify images
into, only to be specified if `include_top` is True, and
if no `weights` argument is specified.
# Returns
A Keras model instance.
# Raises
ValueError: in case of invalid argument for `weights`,
or invalid input shape.
"""
# Determine proper input shape
if input_shape is None:
if K.image_data_format() == 'channels_first':
input_shape = (3, 32, 32) if include_top else (3, None, None)
else:
input_shape = (32, 32, 3) if include_top else (None, None, 3)
# Build network
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
if not K.is_keras_tensor(input_tensor):
img_input = Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
if K.image_data_format() == 'channels_last':
bn_axis = 3
else:
bn_axis = 1
x = Conv2D(filters[0], (3, 3),
padding='same',
name='conv0',
kernel_regularizer=regularizer)(img_input)
if bn:
x = BatchNormalization(axis=bn_axis, name='bn0')(x)
x = Activation(activation)(x)
x = unit(x, [filters[0], filters[0]],
n,
'1-',
kernel_size=3,
stride=1,
regularizer=regularizer,
activation=activation,
conv_shortcut=conv_shortcut,
bn=bn)
for i in range(1, len(filters)):
x = unit(x, [filters[i - 1], filters[i]],
n,
str(i + 1) + '-',
kernel_size=3,
stride=2,
regularizer=regularizer,
activation=activation,
conv_shortcut=conv_shortcut,
bn=bn)
if pooling == 'avg':
x = GlobalAveragePooling2D(name='avg_pool')(x)
elif pooling == 'max':
x = GlobalMaxPooling2D(name='max_pool')(x)
if include_top:
x = Dense(classes,
activation=top_activation,
name='embedding' if top_activation is None else 'prob',
kernel_regularizer=regularizer)(x)
# Ensure that the model takes into account
# any potential predecessors of `input_tensor`.
if input_tensor is not None:
inputs = get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model.
model = Model(inputs,
x,
name='cifar-resnet{}'.format(2 * len(filters) *
n) if name is None else name)
# load weights
if weights is not None:
model.load_weights(weights)
if K.image_data_format() == 'channels_first' and K.backend(
) == 'tensorflow':
warnings.warn('You are using the TensorFlow backend, yet you '
'are using the Theano '
'image data format convention '
'(`image_data_format="channels_first"`). '
'For best performance, set '
'`image_data_format="channels_last"` in '
'your Keras config '
'at ~/.keras/keras.json.')
return model
def MobileNetV3(
stack_fn,
last_point_ch,
input_shape=None,
alpha=1.0,
model_type="large",
minimalistic=False,
include_top=True,
weights="imagenet",
input_tensor=None,
classes=1000,
pooling=None,
dropout_rate=0.2,
classifier_activation="softmax",
include_preprocessing=True,
):
if not (weights in {"imagenet", None} or tf.io.gfile.exists(weights)):
raise ValueError("The `weights` argument should be either "
"`None` (random initialization), `imagenet` "
"(pre-training on ImageNet), "
"or the path to the weights file to be loaded. "
f"Received weights={weights}")
if weights == "imagenet" and include_top and classes != 1000:
raise ValueError(
'If using `weights` as `"imagenet"` with `include_top` '
"as true, `classes` should be 1000. "
f"Received classes={classes}")
# Determine proper input shape and default size.
# If both input_shape and input_tensor are used, they should match
if input_shape is not None and input_tensor is not None:
try:
is_input_t_tensor = backend.is_keras_tensor(input_tensor)
except ValueError:
try:
is_input_t_tensor = backend.is_keras_tensor(
layer_utils.get_source_inputs(input_tensor))
except ValueError:
raise ValueError(
"input_tensor: ",
input_tensor,
"is not type input_tensor. "
f"Received type(input_tensor)={type(input_tensor)}",
)
if is_input_t_tensor:
if backend.image_data_format() == "channels_first":
if backend.int_shape(input_tensor)[1] != input_shape[1]:
raise ValueError(
"When backend.image_data_format()=channels_first, "
"input_shape[1] must equal "
"backend.int_shape(input_tensor)[1]. Received "
f"input_shape={input_shape}, "
"backend.int_shape(input_tensor)="
f"{backend.int_shape(input_tensor)}")
else:
if backend.int_shape(input_tensor)[2] != input_shape[1]:
raise ValueError(
"input_shape[1] must equal "
"backend.int_shape(input_tensor)[2]. Received "
f"input_shape={input_shape}, "
"backend.int_shape(input_tensor)="
f"{backend.int_shape(input_tensor)}")
else:
raise ValueError(
"input_tensor specified: ",
input_tensor,
"is not a keras tensor",
)
# If input_shape is None, infer shape from input_tensor
if input_shape is None and input_tensor is not None:
try:
backend.is_keras_tensor(input_tensor)
except ValueError:
raise ValueError(
"input_tensor: ",
input_tensor,
"is type: ",
type(input_tensor),
"which is not a valid type",
)
if backend.is_keras_tensor(input_tensor):
if backend.image_data_format() == "channels_first":
rows = backend.int_shape(input_tensor)[2]
cols = backend.int_shape(input_tensor)[3]
input_shape = (3, cols, rows)
else:
rows = backend.int_shape(input_tensor)[1]
cols = backend.int_shape(input_tensor)[2]
input_shape = (cols, rows, 3)
# If input_shape is None and input_tensor is None using standard shape
if input_shape is None and input_tensor is None:
input_shape = (None, None, 3)
if backend.image_data_format() == "channels_last":
row_axis, col_axis = (0, 1)
else:
row_axis, col_axis = (1, 2)
rows = input_shape[row_axis]
cols = input_shape[col_axis]
if rows and cols and (rows < 32 or cols < 32):
raise ValueError(
"Input size must be at least 32x32; Received `input_shape="
f"{input_shape}`")
if weights == "imagenet":
if (not minimalistic and alpha not in [0.75, 1.0]
or minimalistic and alpha != 1.0):
raise ValueError(
"If imagenet weights are being loaded, "
"alpha can be one of `0.75`, `1.0` for non minimalistic "
"or `1.0` for minimalistic only.")
if rows != cols or rows != 224:
logging.warning("`input_shape` is undefined or non-square, "
"or `rows` is not 224. "
"Weights for input shape (224, 224) will be "
"loaded as the default.")
if input_tensor is None:
img_input = layers.Input(shape=input_shape)
else:
if not backend.is_keras_tensor(input_tensor):
img_input = layers.Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
channel_axis = 1 if backend.image_data_format() == "channels_first" else -1
if minimalistic:
kernel = 3
activation = relu
se_ratio = None
else:
kernel = 5
activation = hard_swish
se_ratio = 0.25
x = img_input
if include_preprocessing:
x = layers.Rescaling(scale=1.0 / 127.5, offset=-1.0)(x)
x = layers.Conv2D(
16,
kernel_size=3,
strides=(2, 2),
padding="same",
use_bias=False,
name="Conv",
)(x)
x = layers.BatchNormalization(axis=channel_axis,
epsilon=1e-3,
momentum=0.999,
name="Conv/BatchNorm")(x)
x = activation(x)
x = stack_fn(x, kernel, activation, se_ratio)
last_conv_ch = _depth(backend.int_shape(x)[channel_axis] * 6)
# if the width multiplier is greater than 1 we
# increase the number of output channels
if alpha > 1.0:
last_point_ch = _depth(last_point_ch * alpha)
x = layers.Conv2D(
last_conv_ch,
kernel_size=1,
padding="same",
use_bias=False,
name="Conv_1",
)(x)
x = layers.BatchNormalization(axis=channel_axis,
epsilon=1e-3,
momentum=0.999,
name="Conv_1/BatchNorm")(x)
x = activation(x)
if include_top:
x = layers.GlobalAveragePooling2D(keepdims=True)(x)
x = layers.Conv2D(
last_point_ch,
kernel_size=1,
padding="same",
use_bias=True,
name="Conv_2",
)(x)
x = activation(x)
if dropout_rate > 0:
x = layers.Dropout(dropout_rate)(x)
x = layers.Conv2D(classes,
kernel_size=1,
padding="same",
name="Logits")(x)
x = layers.Flatten()(x)
imagenet_utils.validate_activation(classifier_activation, weights)
x = layers.Activation(activation=classifier_activation,
name="Predictions")(x)
else:
if pooling == "avg":
x = layers.GlobalAveragePooling2D(name="avg_pool")(x)
elif pooling == "max":
x = layers.GlobalMaxPooling2D(name="max_pool")(x)
# Ensure that the model takes into account
# any potential predecessors of `input_tensor`.
if input_tensor is not None:
inputs = layer_utils.get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model.
model = models.Model(inputs, x, name="MobilenetV3" + model_type)
# Load weights.
if weights == "imagenet":
model_name = "{}{}_224_{}_float".format(
model_type, "_minimalistic" if minimalistic else "", str(alpha))
if include_top:
file_name = "weights_mobilenet_v3_" + model_name + ".h5"
file_hash = WEIGHTS_HASHES[model_name][0]
else:
file_name = "weights_mobilenet_v3_" + model_name + "_no_top_v2.h5"
file_hash = WEIGHTS_HASHES[model_name][1]
weights_path = data_utils.get_file(
file_name,
BASE_WEIGHT_PATH + file_name,
cache_subdir="models",
file_hash=file_hash,
)
model.load_weights(weights_path)
elif weights is not None:
model.load_weights(weights)
return model
def adam_400epochs(path, nome_teste, p):
imagedir = path
cur_dir = os.getcwd()
os.chdir(imagedir) # the parent folder with sub-folders
# Get number of samples per family
list_fams = sorted(os.listdir(os.getcwd()),
key=str.lower) # vector of strings with family names
if list_fams[0] == '.DS_Store':
list_fams.pop(0)
no_imgs = [] # No. of samples per family
for i in range(len(list_fams)):
os.chdir(list_fams[i])
len1 = len(
glob.glob('*.png')) # assuming the images are stored as 'png'
no_imgs.append(len1)
os.chdir('..')
num_samples = np.sum(no_imgs) # total number of all samples
# Compute the labels
y = np.zeros(num_samples)
pos = 0
label = 0
for i in no_imgs:
print("Label:%2d\tFamily: %15s\tNumber of images: %d" %
(label, list_fams[label], i))
for j in range(i):
y[pos] = label
pos += 1
label += 1
num_classes = label
# Compute the features
width, height, channels = (224, 224, 3)
X = np.zeros((num_samples, width, height, channels))
cnt = 0
list_paths = [] # List of image paths
print("Processing images ...")
for i in range(len(list_fams)):
for img_file in glob.glob(list_fams[i] + '/*.png'):
print("[%d] Processing image: %s" % (cnt, img_file))
list_paths.append(os.path.join(os.getcwd(), img_file))
img = image.load_img(img_file, target_size=(224, 224))
x = image.img_to_array(img)
x = np.expand_dims(x, axis=0)
x = preprocess_input(x)
X[cnt] = x
cnt += 1
print("Images processed: %d" % cnt)
os.chdir(cur_dir)
# Encoding classes (y) into integers (y_encoded) and then generating one-hot-encoding (Y)
encoder = LabelEncoder()
encoder.fit(y)
y_encoded = encoder.transform(y)
Y = np_utils.to_categorical(y_encoded)
############################################## Creating ResNet50 Architecture #############################
image_shape = (224, 224, 3)
weights = 'imagenet'
input_shape = image_shape
include_top = False
input_tensor = None
pooling = None
classes = 1000
if weights not in {'imagenet', None}:
raise ValueError('The `weights` argument should be either '
'`None` (random initialization) or `imagenet` '
'(pre-training on ImageNet).')
if weights == 'imagenet' and include_top and classes != 1000:
raise ValueError('If using `weights` as imagenet with `include_top`'
' as true, `classes` should be 1000')
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
if not K.is_keras_tensor(input_tensor):
img_input = Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
if K.image_data_format() == 'channels_last':
bn_axis = 3
else:
bn_axis = 1
x = Conv2D(64, (7, 7), strides=(2, 2), padding='same',
name='conv1')(img_input)
x = BatchNormalization(axis=bn_axis, name='bn_conv1')(x)
x = Activation('relu')(x)
x = MaxPooling2D((3, 3), strides=(2, 2))(x)
x = conv_block(x, 3, [64, 64, 256], stage=2, block='a', strides=(1, 1))
x = identity_block(x, 3, [64, 64, 256], stage=2, block='b')
x = identity_block(x, 3, [64, 64, 256], stage=2, block='c')
x = conv_block(x, 3, [128, 128, 512], stage=3, block='a')
x = identity_block(x, 3, [128, 128, 512], stage=3, block='b')
x = identity_block(x, 3, [128, 128, 512], stage=3, block='c')
x = identity_block(x, 3, [128, 128, 512], stage=3, block='d')
x = conv_block(x, 3, [256, 256, 1024], stage=4, block='a')
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='b')
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='c')
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='d')
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='e')
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='f')
x = conv_block(x, 3, [512, 512, 2048], stage=5, block='a')
x = identity_block(x, 3, [512, 512, 2048], stage=5, block='b')
x = identity_block(x, 3, [512, 512, 2048], stage=5, block='c')
x = AveragePooling2D((7, 7), name='avg_pool')(x)
if include_top:
x = Flatten()(x)
x = Dense(classes, activation='softmax', name='fc1000')(x)
else:
if pooling == 'avg':
x = GlobalAveragePooling2D()(x)
elif pooling == 'max':
x = GlobalMaxPooling2D()(x)
# Ensure that the model takes into account
# any potential predecessors of `input_tensor`.
if input_tensor is not None:
inputs = get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model.
model_layers = x
model = Model(inputs, x, name='resnet50')
# load weights
if weights == 'imagenet':
if include_top:
weights_path = get_file(
'resnet50_weights_tf_dim_ordering_tf_kernels.h5',
WEIGHTS_PATH,
cache_subdir='models',
md5_hash='a7b3fe01876f51b976af0dea6bc144eb')
else:
weights_path = get_file(
'resnet50_weights_tf_dim_ordering_tf_kernels_notop.h5',
WEIGHTS_PATH_NO_TOP,
cache_subdir='models',
md5_hash='a268eb855778b3df3c7506639542a6af')
model.load_weights(weights_path)
if K.backend() == 'theano':
layer_utils.convert_all_kernels_in_model(model)
if include_top:
maxpool = model.get_layer(name='avg_pool')
shape = maxpool.output_shape[1:]
dense = model.get_layer(name='fc1000')
layer_utils.convert_dense_weights_data_format(
dense, shape, 'channels_first')
if K.image_data_format() == 'channels_first' and K.backend(
) == 'tensorflow':
warnings.warn('You are using the TensorFlow backend, yet you '
'are using the Theano '
'image data format convention '
'(`image_data_format="channels_first"`). '
'For best performance, set '
'`image_data_format="channels_last"` in '
'your Keras config '
'at ~/.keras/keras.json.')
#####################################################################################################
dataset_main_folder = imagedir.rsplit('/', 1)
feature_folder = dataset_main_folder[0] + '/features/'
filename = feature_folder + nome_teste + '-adam-400-epochs.npy'
if os.path.exists(filename):
print("Loading ResNet50 extracted features from %s ..." % filename)
resnet50features = np.load(filename)
else:
print("Extracting features from ResNet50 layers ...")
resnet50features = model.predict(X)
print("Saving ResNet50 extracted features into %s ..." % filename)
os.makedirs(feature_folder)
np.save(filename, resnet50features)
# Create stratified k-fold subsets
kfold = 10 # no. of folds
skf = StratifiedKFold(kfold, shuffle=True, random_state=1)
skfind = [
None
] * kfold # skfind[i][0] -> train indices, skfind[i][1] -> test indices
cnt = 0
for index in skf.split(X, y):
skfind[cnt] = index
cnt += 1
# Training top_model and saving min training loss weights
num_epochs = 4
history = []
conf_mat = np.zeros(
(len(list_fams), len(list_fams))) # Initializing the Confusion Matrix
top_model = None
filenametopweights = feature_folder + 'weights-' + nome_teste + '-adam-400-epochs.h5'
checkpointer = ModelCheckpoint(filepath=filenametopweights,
monitor='loss',
verbose=0,
save_best_only=True,
save_weights_only=True,
mode='min')
for i in range(kfold):
train_indices = skfind[i][0]
test_indices = skfind[i][1]
X_train = resnet50features[train_indices]
Y_train = Y[train_indices]
X_test = resnet50features[test_indices]
Y_test = Y[test_indices]
y_test = y[test_indices]
top_input = Input(shape=resnet50features.shape[1:])
x = GlobalAveragePooling2D(name='avg_pool')(top_input)
predict = Dense(num_classes, activation='softmax',
name='predictions')(x)
top_model = Model(input=top_input, output=predict)
top_model.compile(optimizer='Adam',
loss='categorical_crossentropy',
metrics=['accuracy'])
h = top_model.fit(X_train,
Y_train,
validation_data=(X_test, Y_test),
epochs=num_epochs,
batch_size=X_train.shape[0],
verbose=1,
callbacks=[checkpointer])
history.append(h)
y_prob = top_model.predict(X_test, verbose=0) # Testing
y_pred = np.argmax(y_prob, axis=1)
print("[%d] Test acurracy: %.4f" % (i, accuracy_score(y_test, y_pred)))
cm = confusion_matrix(y_test,
y_pred) # Compute confusion matrix for this fold
conf_mat = conf_mat + cm # Compute global confusion matrix
# Computing the average accuracy
avg_acc = np.trace(conf_mat) / sum(no_imgs)
print("\nAverage acurracy: %.4f" % avg_acc)
# Ploting the confusion matrix
conf_mat = conf_mat.T # since rows and cols are interchangeable
conf_mat_norm = conf_mat / no_imgs # Normalizing the confusion matrix
conf_mat = np.around(conf_mat_norm,
decimals=2) # rounding to display in figure
figure = plt.gcf()
figure.set_size_inches(14, 10)
plt.imshow(conf_mat, interpolation='nearest')
for row in range(len(list_fams)):
for col in range(len(list_fams)):
plt.annotate(str(conf_mat[row][col]),
xy=(col, row),
ha='center',
va='center')
plt.xticks(range(len(list_fams)), list_fams, rotation=90, fontsize=10)
plt.yticks(range(len(list_fams)), list_fams, fontsize=10)
plt.title(path + 'Adam 400 epochs')
plt.colorbar()
path_resultados = "../resultados/" + nome_teste
if not os.path.exists(path_resultados):
os.makedirs(path_resultados)
plt.savefig(path_resultados + "/Adam-400epochs.jpg")
plt.cla()
plt.clf()
plot_acc(history, path_resultados + "/Adam-400epochs-acc.jpg")
plt.cla()
plt.clf()
plot_loss(history, path_resultados + "/Adam-400epochs-loss.jpg")
plt.cla()
plt.clf()
############### Stacking top model ################
# top_input = Input(shape=resnet50features.shape[1:])
# x = GlobalAveragePooling2D(name='final_pool')(model_layers)
x = Dense(num_classes, activation='softmax',
name='predictions')(model_layers)
model = Model(inputs, x, name='resnet50')
model.load_weights(filenametopweights, by_name=True)
model.compile(optimizer='Adam',
loss='categorical_crossentropy',
metrics=['accuracy'])
layer_name = 'predictions'
layer_idx = [
idx for idx, layer in enumerate(model.layers)
if layer.name == layer_name
][0]
numimgheatmap = 1
path_txt = path_resultados + "/" + nome_teste + "-PredClass.txt"
txt_file = open(path_txt, 'w')
for fam in list_fams:
path_resultados_orig = path_resultados
print("Class: %s" % (fam))
fam_samples = [
name for name in list_paths if fam in name.split('/')[-2:-1]
]
print(len(fam_samples))
image_paths = fam_samples
heatmaps = []
myfig = plt.figure()
plt.axis('off')
path_resultados = path_resultados_orig + "/heatmaps/" + fam + "/"
if not os.path.exists(path_resultados):
os.makedirs(path_resultados)
for path in image_paths:
seed_img = image.load_img(path, target_size=(224, 224))
seed_img = image.img_to_array(seed_img)
img_orig = seed_img
seed_img = np.expand_dims(seed_img, axis=0)
pred_class = np.argmax(model.predict(seed_img))
aux = path.split('/')
imagem = aux[len(aux) - 1]
heatMapName = path_resultados + "heatmap-" + imagem[:-4] + ".png"
heatMapNameArray = path_resultados + "HMarr-" + imagem[:-4] + ".npy"
print(len(model.layers))
heatmap = visualize_class_activation_map(model, path, heatMapName)
# heatmap = visualize_cam(model, layer_idx, [pred_class], seed_img)
np.save(heatMapNameArray, heatmap)
plt.imsave(fname=heatMapName, arr=heatmap)
orig = np.array(img_orig, dtype=np.float)
orig /= 255
heatmap = np.array(heatmap, dtype=np.float)
heatmap /= 255
a_channel = np.ones(orig.shape, dtype=np.float) / 3.7
image_final = (heatmap * a_channel) + (orig * (1 - a_channel))
txt_file.write("Image: %s - Class: %s - Pred: %d (%s)\n" %
(path.split('/')[-1:], path.split('/')[-2:-1],
pred_class, list_fams[pred_class]))
print("Image: %s" % (path.split('/')[-1:]))
heatMapNameMerge = path_resultados + "/heatmap-" + imagem[:-4] + "-merge.png"
plt.imsave(fname=heatMapNameMerge, arr=image_final)
def InceptionResNetV2(include_top=True,
weights='imagenet',
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000):
"""Instantiates the Inception-ResNet v2 architecture.
Optionally loads weights pre-trained on ImageNet.
Note that when using TensorFlow, for best performance you should
set `"image_data_format": "channels_last"` in your Keras config
at `~/.keras/keras.json`.
The model and the weights are compatible with TensorFlow, Theano and
CNTK backends. The data format convention used by the model is
the one specified in your Keras config file.
Note that the default input image size for this model is 299x299, instead
of 224x224 as in the VGG16 and ResNet models. Also, the input preprocessing
function is different (i.e., do not use `imagenet_utils.preprocess_input()`
with this model. Use `preprocess_input()` defined in this module instead).
# Arguments
include_top: whether to include the fully-connected
layer at the top of the network.
weights: one of `None` (random initialization),
'imagenet' (pre-training on ImageNet),
or the path to the weights file to be loaded.
input_tensor: optional Keras tensor (i.e. output of `layers.Input()`)
to use as image input for the model.
input_shape: optional shape tuple, only to be specified
if `include_top` is `False` (otherwise the input shape
has to be `(299, 299, 3)` (with `'channels_last'` data format)
or `(3, 299, 299)` (with `'channels_first'` data format).
It should have exactly 3 inputs channels,
and width and height should be no smaller than 139.
E.g. `(150, 150, 3)` would be one valid value.
pooling: Optional pooling mode for feature extraction
when `include_top` is `False`.
- `None` means that the output of the model will be
the 4D tensor output of the last convolutional layer.
- `'avg'` means that global average pooling
will be applied to the output of the
last convolutional layer, and thus
the output of the model will be a 2D tensor.
- `'max'` means that global max pooling will be applied.
classes: optional number of classes to classify images
into, only to be specified if `include_top` is `True`, and
if no `weights` argument is specified.
# Returns
A Keras `Model` instance.
# Raises
ValueError: in case of invalid argument for `weights`,
or invalid input shape.
"""
if not (weights in {'imagenet', None} or os.path.exists(weights)):
raise ValueError('The `weights` argument should be either '
'`None` (random initialization), `imagenet` '
'(pre-training on ImageNet), '
'or the path to the weights file to be loaded.')
if weights == 'imagenet' and include_top and classes != 1000:
raise ValueError('If using `weights` as imagenet with `include_top`'
' as true, `classes` should be 1000')
# Determine proper input shape
input_shape = _obtain_input_shape(
input_shape,
default_size=299,
min_size=139,
data_format=K.image_data_format(),
require_flatten=False,
weights=weights)
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
if not K.is_keras_tensor(input_tensor):
img_input = Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
# Stem block: 35 x 35 x 192
x = conv2d_bn(img_input, 32, 3, strides=2, padding='same')
x = conv2d_bn(x, 32, 3, padding='same')
x = conv2d_bn(x, 64, 3)
x = MaxPooling2D(3, strides=2, padding='same')(x)
x = conv2d_bn(x, 80, 1, padding='same')
x = conv2d_bn(x, 192, 3, padding='same')
x = MaxPooling2D(3, strides=2, padding='same')(x)
# Mixed 5b (Inception-A block): 35 x 35 x 320
branch_0 = conv2d_bn(x, 96, 1)
branch_1 = conv2d_bn(x, 48, 1)
branch_1 = conv2d_bn(branch_1, 64, 5)
branch_2 = conv2d_bn(x, 64, 1)
branch_2 = conv2d_bn(branch_2, 96, 3)
branch_2 = conv2d_bn(branch_2, 96, 3)
branch_pool = AveragePooling2D(3, strides=1, padding='same')(x)
branch_pool = conv2d_bn(branch_pool, 64, 1)
branches = [branch_0, branch_1, branch_2, branch_pool]
channel_axis = 1 if K.image_data_format() == 'channels_first' else 3
x = Concatenate(axis=channel_axis, name='mixed_5b')(branches)
# 10x block35 (Inception-ResNet-A block): 35 x 35 x 320
for block_idx in range(1, 11):
x = inception_resnet_block(x,
scale=0.17,
block_type='block35',
block_idx=block_idx)
# Mixed 6a (Reduction-A block): 17 x 17 x 1088
branch_0 = conv2d_bn(x, 384, 3, strides=2, padding='same')
branch_1 = conv2d_bn(x, 256, 1)
branch_1 = conv2d_bn(branch_1, 256, 3)
branch_1 = conv2d_bn(branch_1, 384, 3, strides=2, padding='same')
branch_pool = MaxPooling2D(3, strides=2, padding='same')(x)
branches = [branch_0, branch_1, branch_pool]
x = Concatenate(axis=channel_axis, name='mixed_6a')(branches)
# 20x block17 (Inception-ResNet-B block): 17 x 17 x 1088
for block_idx in range(1, 21):
x = inception_resnet_block(x,
scale=0.1,
block_type='block17',
block_idx=block_idx)
# Mixed 7a (Reduction-B block): 8 x 8 x 2080
branch_0 = conv2d_bn(x, 256, 1)
branch_0 = conv2d_bn(branch_0, 384, 3, strides=2, padding='same')
branch_1 = conv2d_bn(x, 256, 1)
branch_1 = conv2d_bn(branch_1, 288, 3, strides=2, padding='same')
branch_2 = conv2d_bn(x, 256, 1)
branch_2 = conv2d_bn(branch_2, 288, 3)
branch_2 = conv2d_bn(branch_2, 320, 3, strides=2, padding='same')
branch_pool = MaxPooling2D(3, strides=2, padding='same')(x)
branches = [branch_0, branch_1, branch_2, branch_pool]
x = Concatenate(axis=channel_axis, name='mixed_7a')(branches)
# 10x block8 (Inception-ResNet-C block): 8 x 8 x 2080
for block_idx in range(1, 10):
x = inception_resnet_block(x,
scale=0.2,
block_type='block8',
block_idx=block_idx)
x = inception_resnet_block(x,
scale=1.,
activation=None,
block_type='block8',
block_idx=10)
# Final convolution block: 8 x 8 x 1536
x = conv2d_bn(x, 1536, 1, name='conv_7b')
if include_top:
# Classification block
x = GlobalAveragePooling2D(name='avg_pool')(x)
x = Dense(classes, activation='softmax', name='predictions')(x)
else:
if pooling == 'avg':
x = GlobalAveragePooling2D()(x)
elif pooling == 'max':
x = GlobalMaxPooling2D()(x)
# Ensure that the model takes into account
# any potential predecessors of `input_tensor`
if input_tensor is not None:
inputs = get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model
model = Model(inputs, x, name='inception_resnet_v2')
# Load weights
if weights == 'imagenet':
if K.image_data_format() == 'channels_first':
if K.backend() == 'tensorflow':
warnings.warn('You are using the TensorFlow backend, yet you '
'are using the Theano '
'image data format convention '
'(`image_data_format="channels_first"`). '
'For best performance, set '
'`image_data_format="channels_last"` in '
'your Keras config '
'at ~/.keras/keras.json.')
if include_top:
fname = 'inception_resnet_v2_weights_tf_dim_ordering_tf_kernels.h5'
weights_path = get_file(fname,
BASE_WEIGHT_URL + fname,
cache_subdir='models',
file_hash='e693bd0210a403b3192acc6073ad2e96')
else:
fname = 'inception_resnet_v2_weights_tf_dim_ordering_tf_kernels_notop.h5'
weights_path = get_file(fname,
BASE_WEIGHT_URL + fname,
cache_subdir='models',
file_hash='d19885ff4a710c122648d3b5c3b684e4')
model.load_weights(weights_path)
elif weights is not None:
model.load_weights(weights)
return model
def Deeplabv3(weights='pascal_voc',
input_tensor=None,
input_shape=(512, 512, 3),
classes=21,
backbone='mobilenetv2',
OS=16,
alpha=1.):
""" Instantiates the Deeplabv3+ architecture
Optionally loads weights pre-trained
on PASCAL VOC. This model is available for TensorFlow only,
and can only be used with inputs following the TensorFlow
data format `(width, height, channels)`.
# Arguments
weights: one of 'pascal_voc' (pre-trained on pascal voc)
or None (random initialization)
input_tensor: optional Keras tensor (i.e. output of `layers.Input()`)
to use as image input for the model.
input_shape: shape of input image. format HxWxC
PASCAL VOC model was trained on (512,512,3) images
classes: number of desired classes. If classes != 21,
last layer is initialized randomly
backbone: backbone to use. one of {'xception','mobilenetv2'}
OS: determines input_shape/feature_extractor_output ratio. One of {8,16}.
Used only for xception backbone.
alpha: controls the width of the MobileNetV2 network. This is known as the
width multiplier in the MobileNetV2 paper.
- If `alpha` < 1.0, proportionally decreases the number
of filters in each layer.
- If `alpha` > 1.0, proportionally increases the number
of filters in each layer.
- If `alpha` = 1, default number of filters from the paper
are used at each layer.
Used only for mobilenetv2 backbone
# Returns
A Keras model instance.
# Raises
RuntimeError: If attempting to run this model with a
backend that does not support separable convolutions.
ValueError: in case of invalid argument for `weights` or `backbone`
"""
if not (weights in {'pascal_voc', 'cityscapes', None}):
raise ValueError(
'The `weights` argument should be either '
'`None` (random initialization), `pascal_voc`, or `cityscapes` '
'(pre-trained on PASCAL VOC)')
if K.backend() != 'tensorflow':
raise RuntimeError('The Deeplabv3+ model is only available with '
'the TensorFlow backend.')
if not (backbone in {'xception', 'mobilenetv2'}):
raise ValueError('The `backbone` argument should be either '
'`xception` or `mobilenetv2` ')
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
if not K.is_keras_tensor(input_tensor):
img_input = Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
if backbone == 'xception':
if OS == 8:
entry_block3_stride = 1
middle_block_rate = 2 # ! Not mentioned in paper, but required
exit_block_rates = (2, 4)
atrous_rates = (12, 24, 36)
else:
entry_block3_stride = 2
middle_block_rate = 1
exit_block_rates = (1, 2)
atrous_rates = (6, 12, 18)
x = Conv2D(32, (3, 3),
strides=(2, 2),
name='entry_flow_conv1_1',
use_bias=False,
padding='same')(img_input)
x = BatchNormalization(name='entry_flow_conv1_1_BN')(x)
x = Activation('relu')(x)
x = _conv2d_same(x, 64, 'entry_flow_conv1_2', kernel_size=3, stride=1)
x = BatchNormalization(name='entry_flow_conv1_2_BN')(x)
x = Activation('relu')(x)
x = _xception_block(x, [128, 128, 128],
'entry_flow_block1',
skip_connection_type='conv',
stride=2,
depth_activation=False)
x, skip1 = _xception_block(x, [256, 256, 256],
'entry_flow_block2',
skip_connection_type='conv',
stride=2,
depth_activation=False,
return_skip=True)
x = _xception_block(x, [728, 728, 728],
'entry_flow_block3',
skip_connection_type='conv',
stride=entry_block3_stride,
depth_activation=False)
for i in range(16):
x = _xception_block(x, [728, 728, 728],
'middle_flow_unit_{}'.format(i + 1),
skip_connection_type='sum',
stride=1,
rate=middle_block_rate,
depth_activation=False)
x = _xception_block(x, [728, 1024, 1024],
'exit_flow_block1',
skip_connection_type='conv',
stride=1,
rate=exit_block_rates[0],
depth_activation=False)
x = _xception_block(x, [1536, 1536, 2048],
'exit_flow_block2',
skip_connection_type='none',
stride=1,
rate=exit_block_rates[1],
depth_activation=True)
else:
OS = 8
first_block_filters = _make_divisible(32 * alpha, 8)
x = Conv2D(first_block_filters,
kernel_size=3,
strides=(2, 2),
padding='same',
use_bias=False,
name='Conv')(img_input)
x = BatchNormalization(epsilon=1e-3, momentum=0.999, name='Conv_BN')(x)
x = Activation(relu6, name='Conv_Relu6')(x)
x = _inverted_res_block(x,
filters=16,
alpha=alpha,
stride=1,
expansion=1,
block_id=0,
skip_connection=False)
x = _inverted_res_block(x,
filters=24,
alpha=alpha,
stride=2,
expansion=6,
block_id=1,
skip_connection=False)
x = _inverted_res_block(x,
filters=24,
alpha=alpha,
stride=1,
expansion=6,
block_id=2,
skip_connection=True)
x = _inverted_res_block(x,
filters=32,
alpha=alpha,
stride=2,
expansion=6,
block_id=3,
skip_connection=False)
x = _inverted_res_block(x,
filters=32,
alpha=alpha,
stride=1,
expansion=6,
block_id=4,
skip_connection=True)
x = _inverted_res_block(x,
filters=32,
alpha=alpha,
stride=1,
expansion=6,
block_id=5,
skip_connection=True)
# stride in block 6 changed from 2 -> 1, so we need to use rate = 2
x = _inverted_res_block(
x,
filters=64,
alpha=alpha,
stride=1, # 1!
expansion=6,
block_id=6,
skip_connection=False)
x = _inverted_res_block(x,
filters=64,
alpha=alpha,
stride=1,
rate=2,
expansion=6,
block_id=7,
skip_connection=True)
x = _inverted_res_block(x,
filters=64,
alpha=alpha,
stride=1,
rate=2,
expansion=6,
block_id=8,
skip_connection=True)
x = _inverted_res_block(x,
filters=64,
alpha=alpha,
stride=1,
rate=2,
expansion=6,
block_id=9,
skip_connection=True)
x = _inverted_res_block(x,
filters=96,
alpha=alpha,
stride=1,
rate=2,
expansion=6,
block_id=10,
skip_connection=False)
x = _inverted_res_block(x,
filters=96,
alpha=alpha,
stride=1,
rate=2,
expansion=6,
block_id=11,
skip_connection=True)
x = _inverted_res_block(x,
filters=96,
alpha=alpha,
stride=1,
rate=2,
expansion=6,
block_id=12,
skip_connection=True)
x = _inverted_res_block(
x,
filters=160,
alpha=alpha,
stride=1,
rate=2, # 1!
expansion=6,
block_id=13,
skip_connection=False)
x = _inverted_res_block(x,
filters=160,
alpha=alpha,
stride=1,
rate=4,
expansion=6,
block_id=14,
skip_connection=True)
x = _inverted_res_block(x,
filters=160,
alpha=alpha,
stride=1,
rate=4,
expansion=6,
block_id=15,
skip_connection=True)
x = _inverted_res_block(x,
filters=320,
alpha=alpha,
stride=1,
rate=4,
expansion=6,
block_id=16,
skip_connection=False)
# end of feature extractor
# branching for Atrous Spatial Pyramid Pooling
# Image Feature branch
#out_shape = int(np.ceil(input_shape[0] / OS))
b4 = AveragePooling2D(pool_size=(int(np.ceil(input_shape[0] / OS)),
int(np.ceil(input_shape[1] / OS))))(x)
b4 = Conv2D(256, (1, 1),
padding='same',
use_bias=False,
name='image_pooling')(b4)
b4 = BatchNormalization(name='image_pooling_BN', epsilon=1e-5)(b4)
b4 = Activation('relu')(b4)
b4 = BilinearUpsampling((int(np.ceil(input_shape[0] / OS)),
int(np.ceil(input_shape[1] / OS))))(b4)
# simple 1x1
b0 = Conv2D(256, (1, 1), padding='same', use_bias=False, name='aspp0')(x)
b0 = BatchNormalization(name='aspp0_BN', epsilon=1e-5)(b0)
b0 = Activation('relu', name='aspp0_activation')(b0)
# there are only 2 branches in mobilenetV2. not sure why
if backbone == 'xception':
# rate = 6 (12)
b1 = SepConv_BN(x,
256,
'aspp1',
rate=atrous_rates[0],
depth_activation=True,
epsilon=1e-5)
# rate = 12 (24)
b2 = SepConv_BN(x,
256,
'aspp2',
rate=atrous_rates[1],
depth_activation=True,
epsilon=1e-5)
# rate = 18 (36)
b3 = SepConv_BN(x,
256,
'aspp3',
rate=atrous_rates[2],
depth_activation=True,
epsilon=1e-5)
# concatenate ASPP branches & project
x = Concatenate()([b4, b0, b1, b2, b3])
else:
x = Concatenate()([b4, b0])
x = Conv2D(256, (1, 1),
padding='same',
use_bias=False,
name='concat_projection')(x)
x = BatchNormalization(name='concat_projection_BN', epsilon=1e-5)(x)
x = Activation('relu')(x)
x = Dropout(0.1)(x)
# DeepLab v.3+ decoder
if backbone == 'xception':
# Feature projection
# x4 (x2) block
x = BilinearUpsampling(output_size=(int(np.ceil(input_shape[0] / 4)),
int(np.ceil(input_shape[1] /
4))))(x)
dec_skip1 = Conv2D(48, (1, 1),
padding='same',
use_bias=False,
name='feature_projection0')(skip1)
dec_skip1 = BatchNormalization(name='feature_projection0_BN',
epsilon=1e-5)(dec_skip1)
dec_skip1 = Activation('relu')(dec_skip1)
x = Concatenate()([x, dec_skip1])
x = SepConv_BN(x,
256,
'decoder_conv0',
depth_activation=True,
epsilon=1e-5)
x = SepConv_BN(x,
256,
'decoder_conv1',
depth_activation=True,
epsilon=1e-5)
# you can use it with arbitary number of classes
if classes == 21:
last_layer_name = 'logits_semantic'
else:
last_layer_name = 'custom_logits_semantic'
x = Conv2D(classes, (1, 1), padding='same', name=last_layer_name)(x)
x = BilinearUpsampling(output_size=(input_shape[0], input_shape[1]))(x)
# Ensure that the model takes into account
# any potential predecessors of `input_tensor`.
if input_tensor is not None:
inputs = get_source_inputs(input_tensor)
else:
inputs = img_input
model = Model(inputs, x, name='deeplabv3plus')
# load weights
if weights == 'pascal_voc':
if backbone == 'xception':
weights_path = get_file(
'deeplabv3_xception_tf_dim_ordering_tf_kernels.h5',
WEIGHTS_PATH_X,
cache_subdir='models')
else:
weights_path = get_file(
'deeplabv3_mobilenetv2_tf_dim_ordering_tf_kernels.h5',
WEIGHTS_PATH_MOBILE,
cache_subdir='models')
model.load_weights(weights_path, by_name=True)
elif weights == 'cityscapes':
if backbone == 'xception':
weights_path = get_file(
'deeplabv3_xception_tf_dim_ordering_tf_kernels_cityscapes.h5',
WEIGHTS_PATH_X_CS,
cache_subdir='models')
else:
weights_path = get_file(
'deeplabv3_mobilenetv2_tf_dim_ordering_tf_kernels_cityscapes.h5',
WEIGHTS_PATH_MOBILE_CS,
cache_subdir='models')
model.load_weights(weights_path, by_name=True)
return model
def ResNet50(nb_rows, nb_cols, include_top=True, weights='imagenet',
input_tensor=None, nb_classes=10):
'''Instantiate the ResNet50 architecture,
optionally loading weights pre-trained
on ImageNet. Note that when using TensorFlow,
for best performance you should set
`image_dim_ordering="tf"` in your Keras config
at ~/.keras/keras.json.
The model and the weights are compatible with both
TensorFlow and Theano. The dimension ordering
convention used by the model is the one
specified in your Keras config file.
# Arguments
include_top: whether to include the 3 fully-connected
layers at the top of the network.
weights: one of `None` (random initialization)
or "imagenet" (pre-training on ImageNet).
input_tensor: optional Keras tensor (i.e. xput of `layers.Input()`)
to use as image input for the model.
# Returns
A Keras model instance.
'''
if weights not in {'imagenet', None}:
raise ValueError('The `weights` argument should be either '
'`None` (random initialization) or `imagenet` '
'(pre-training on ImageNet).')
# Determine proper input shape
if K.image_dim_ordering() == 'th':
if include_top:
input_shape = (1, nb_rows, nb_cols)
else:
input_shape = (1, None, None)
else:
if include_top:
input_shape = (nb_rows, nb_cols, 1)
else:
input_shape = (None, None, 1)
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
if not K.is_keras_tensor(input_tensor):
img_input = Input(tensor=input_tensor)
else:
img_input = input_tensor
if K.image_dim_ordering() == 'tf':
bn_axis = 3
else:
bn_axis = 1
x = ZeroPadding2D((3, 3))(img_input)
x = Convolution2D(64, 7, 7, subsample=(2, 2), name='conv1')(x)
x = BatchNormalization(axis=bn_axis, name='bn_conv1')(x)
x = Activation('relu')(x)
x = MaxPooling2D((3, 3), strides=(2, 2))(x)
x = conv_block(x, 3, [64, 64, 256], stage=2, block='a', strides=(1, 1))
x = identity_block(x, 3, [64, 64, 256], stage=2, block='b')
x = identity_block(x, 3, [64, 64, 256], stage=2, block='c')
x = conv_block(x, 3, [128, 128, 512], stage=3, block='a')
x = identity_block(x, 3, [128, 128, 512], stage=3, block='b')
x = identity_block(x, 3, [128, 128, 512], stage=3, block='c')
x = identity_block(x, 3, [128, 128, 512], stage=3, block='d')
x = conv_block(x, 3, [256, 256, 1024], stage=4, block='a')
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='b')
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='c')
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='d')
#x = identity_block(x, 3, [256, 256, 1024], stage=4, block='e')
#x = identity_block(x, 3, [256, 256, 1024], stage=4, block='f')
#x = conv_block(x, 3, [512, 512, 2048], stage=5, block='a')
#x = identity_block(x, 3, [512, 512, 2048], stage=5, block='b')
#x = identity_block(x, 3, [512, 512, 2048], stage=5, block='c')
x = AveragePooling2D((7, 7), name='avg_pool')(x)
if include_top:
x = Flatten()(x)
x = Dense(nb_classes, activation='softmax', name='softmax_out')(x)
model = Model(img_input, x)
sgd = SGD(lr=0.01, decay=0, momentum=0.9, nesterov=True)
model.compile(loss='categorical_crossentropy', optimizer=sgd, metrics=['accuracy'])
return model
def Xception_model(include_top=True,
weights='imagenet',
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000):
"""Instantiates the Xception architecture.
Optionally loads weights pre-trained
on ImageNet. This model is available for TensorFlow only,
and can only be used with inputs following the TensorFlow
data format `(width, height, channels)`.
You should set `image_data_format="channels_last"` in your Keras config
located at ~/.keras/keras.json.
Note that the default input image size for this model is 299x299.
# Arguments
include_top: whether to include the fully-connected
layer at the top of the network.
weights: one of `None` (random initialization)
or "imagenet" (pre-training on ImageNet).
input_tensor: optional Keras tensor (i.e. output of `layers.Input()`)
to use as image input for the model.
input_shape: optional shape tuple, only to be specified
if `include_top` is False (otherwise the input shape
has to be `(299, 299, 3)`.
It should have exactly 3 inputs channels,
and width and height should be no smaller than 71.
E.g. `(150, 150, 3)` would be one valid value.
pooling: Optional pooling mode for feature extraction
when `include_top` is `False`.
- `None` means that the output of the model will be
the 4D tensor output of the
last convolutional layer.
- `avg` means that global average pooling
will be applied to the output of the
last convolutional layer, and thus
the output of the model will be a 2D tensor.
- `max` means that global max pooling will
be applied.
classes: optional number of classes to classify images
into, only to be specified if `include_top` is True, and
if no `weights` argument is specified.
# Returns
A Keras model instance.
# Raises
ValueError: in case of invalid argument for `weights`,
or invalid input shape.
RuntimeError: If attempting to run this model with a
backend that does not support separable convolutions.
"""
if weights not in {'imagenet', None}:
raise ValueError('The `weights` argument should be either '
'`None` (random initialization) or `imagenet` '
'(pre-training on ImageNet).')
if weights == 'imagenet' and include_top and classes != 1000:
raise ValueError('If using `weights` as imagenet with `include_top`'
' as true, `classes` should be 1000')
if K.backend() != 'tensorflow':
raise RuntimeError('The Xception model is only available with '
'the TensorFlow backend.')
if K.image_data_format() != 'channels_last':
warnings.warn(
'The Xception model is only available for the '
'input data format "channels_last" '
'(width, height, channels). '
'However your settings specify the default '
'data format "channels_first" (channels, width, height). '
'You should set `image_data_format="channels_last"` in your Keras '
'config located at ~/.keras/keras.json. '
'The model being returned right now will expect inputs '
'to follow the "channels_last" data format.')
K.set_image_data_format('channels_last')
old_data_format = 'channels_first'
else:
old_data_format = None
# Determine proper input shape
input_shape = _obtain_input_shape(input_shape,
default_size=299,
min_size=71,
data_format=K.image_data_format(),
include_top=include_top)
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
if not K.is_keras_tensor(input_tensor):
img_input = Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
x = Conv2D(32, (3, 3), strides=(2, 2), use_bias=False,
name='block1_conv1')(img_input)
x = BatchNormalization(name='block1_conv1_bn')(x)
x = Activation('relu', name='block1_conv1_act')(x)
x = Conv2D(64, (3, 3), use_bias=False, name='block1_conv2')(x)
x = BatchNormalization(name='block1_conv2_bn')(x)
x = Activation('relu', name='block1_conv2_act')(x)
residual = Conv2D(128, (1, 1),
strides=(2, 2),
padding='same',
use_bias=False)(x)
residual = BatchNormalization()(residual)
x = SeparableConv2D(128, (3, 3),
padding='same',
use_bias=False,
name='block2_sepconv1')(x)
x = BatchNormalization(name='block2_sepconv1_bn')(x)
x = Activation('relu', name='block2_sepconv2_act')(x)
x = SeparableConv2D(128, (3, 3),
padding='same',
use_bias=False,
name='block2_sepconv2')(x)
x = BatchNormalization(name='block2_sepconv2_bn')(x)
x = MaxPooling2D((3, 3),
strides=(2, 2),
padding='same',
name='block2_pool')(x)
x = layers.add([x, residual])
residual = Conv2D(256, (1, 1),
strides=(2, 2),
padding='same',
use_bias=False)(x)
residual = BatchNormalization()(residual)
x = Activation('relu', name='block3_sepconv1_act')(x)
x = SeparableConv2D(256, (3, 3),
padding='same',
use_bias=False,
name='block3_sepconv1')(x)
x = BatchNormalization(name='block3_sepconv1_bn')(x)
x = Activation('relu', name='block3_sepconv2_act')(x)
x = SeparableConv2D(256, (3, 3),
padding='same',
use_bias=False,
name='block3_sepconv2')(x)
x = BatchNormalization(name='block3_sepconv2_bn')(x)
x = MaxPooling2D((3, 3),
strides=(2, 2),
padding='same',
name='block3_pool')(x)
x = layers.add([x, residual])
residual = Conv2D(728, (1, 1),
strides=(2, 2),
padding='same',
use_bias=False)(x)
residual = BatchNormalization()(residual)
x = Activation('relu', name='block4_sepconv1_act')(x)
x = SeparableConv2D(728, (3, 3),
padding='same',
use_bias=False,
name='block4_sepconv1')(x)
x = BatchNormalization(name='block4_sepconv1_bn')(x)
x = Activation('relu', name='block4_sepconv2_act')(x)
x = SeparableConv2D(728, (3, 3),
padding='same',
use_bias=False,
name='block4_sepconv2')(x)
x = BatchNormalization(name='block4_sepconv2_bn')(x)
x = MaxPooling2D((3, 3),
strides=(2, 2),
padding='same',
name='block4_pool')(x)
x = layers.add([x, residual])
for i in range(8):
residual = x
prefix = 'block' + str(i + 5)
x = Activation('relu', name=prefix + '_sepconv1_act')(x)
x = SeparableConv2D(728, (3, 3),
padding='same',
use_bias=False,
name=prefix + '_sepconv1')(x)
x = BatchNormalization(name=prefix + '_sepconv1_bn')(x)
x = Activation('relu', name=prefix + '_sepconv2_act')(x)
x = SeparableConv2D(728, (3, 3),
padding='same',
use_bias=False,
name=prefix + '_sepconv2')(x)
x = BatchNormalization(name=prefix + '_sepconv2_bn')(x)
x = Activation('relu', name=prefix + '_sepconv3_act')(x)
x = SeparableConv2D(728, (3, 3),
padding='same',
use_bias=False,
name=prefix + '_sepconv3')(x)
x = BatchNormalization(name=prefix + '_sepconv3_bn')(x)
x = layers.add([x, residual])
residual = Conv2D(1024, (1, 1),
strides=(2, 2),
padding='same',
use_bias=False)(x)
residual = BatchNormalization()(residual)
x = Activation('relu', name='block13_sepconv1_act')(x)
x = SeparableConv2D(728, (3, 3),
padding='same',
use_bias=False,
name='block13_sepconv1')(x)
x = BatchNormalization(name='block13_sepconv1_bn')(x)
x = Activation('relu', name='block13_sepconv2_act')(x)
x = SeparableConv2D(1024, (3, 3),
padding='same',
use_bias=False,
name='block13_sepconv2')(x)
x = BatchNormalization(name='block13_sepconv2_bn')(x)
x = MaxPooling2D((3, 3),
strides=(2, 2),
padding='same',
name='block13_pool')(x)
x = layers.add([x, residual])
x = SeparableConv2D(1536, (3, 3),
padding='same',
use_bias=False,
name='block14_sepconv1')(x)
x = BatchNormalization(name='block14_sepconv1_bn')(x)
x = Activation('relu', name='block14_sepconv1_act')(x)
x = SeparableConv2D(2048, (3, 3),
padding='same',
use_bias=False,
name='block14_sepconv2')(x)
x = BatchNormalization(name='block14_sepconv2_bn')(x)
x = Activation('relu', name='block14_sepconv2_act')(x)
if include_top:
x = GlobalAveragePooling2D(name='avg_pool')(x)
x = Dense(classes, activation='softmax', name='predictions')(x)
else:
if pooling == 'avg':
x = GlobalAveragePooling2D()(x)
elif pooling == 'max':
x = GlobalMaxPooling2D()(x)
# Ensure that the model takes into account
# any potential predecessors of `input_tensor`.
if input_tensor is not None:
inputs = get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model.
model = Model(inputs, x, name='xception')
# load weights
if weights == 'imagenet':
if include_top:
weights_path = get_file(
'xception_weights_tf_dim_ordering_tf_kernels.h5',
TF_WEIGHTS_PATH,
cache_subdir='models')
else:
weights_path = get_file(
'xception_weights_tf_dim_ordering_tf_kernels_notop.h5',
TF_WEIGHTS_PATH_NO_TOP,
cache_subdir='models')
model.load_weights(weights_path)
if old_data_format:
K.set_image_data_format(old_data_format)
# sgd = SGD(lr=1e-3, decay=1e-6, momentum=0.9, nesterov=True)
# model.compile(optimizer=sgd, loss='categorical_crossentropy', metrics=['accuracy'])
#overview of the parameters of model
model.summary()
model.get_config()
return model
def Xception(include_top=True, weights='imagenet',
input_tensor=None):
'''Instantiate the Xception architecture,
optionally loading weights pre-trained
on ImageNet. This model is available for TensorFlow only,
and can only be used with inputs following the TensorFlow
dimension ordering `(width, height, channels)`.
You should set `image_dim_ordering="tf"` in your Keras config
located at ~/.keras/keras.json.
Note that the default input image size for this model is 299x299.
# Arguments
include_top: whether to include the fully-connected
layer at the top of the network.
weights: one of `None` (random initialization)
or "imagenet" (pre-training on ImageNet).
input_tensor: optional Keras tensor (i.e. output of `layers.Input()`)
to use as image input for the model.
# Returns
A Keras model instance.
'''
if weights not in {'imagenet', None}:
raise ValueError('The `weights` argument should be either '
'`None` (random initialization) or `imagenet` '
'(pre-training on ImageNet).')
if K.backend() != 'tensorflow':
raise Exception('The Xception model is only available with '
'the TensorFlow backend.')
if K.image_dim_ordering() != 'tf':
warnings.warn('The Xception model is only available for the '
'input dimension ordering "tf" '
'(width, height, channels). '
'However your settings specify the default '
'dimension ordering "th" (channels, width, height). '
'You should set `image_dim_ordering="tf"` in your Keras '
'config located at ~/.keras/keras.json. '
'The model being returned right now will expect inputs '
'to follow the "tf" dimension ordering.')
K.set_image_dim_ordering('tf')
old_dim_ordering = 'th'
else:
old_dim_ordering = None
# Determine proper input shape
if include_top:
input_shape = (299, 299, 3)
else:
input_shape = (None, None, 3)
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
if not K.is_keras_tensor(input_tensor):
img_input = Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
x = Conv2D(32, 3, 3, subsample=(2, 2), bias=False, name='block1_conv1')(img_input)
x = BatchNormalization(name='block1_conv1_bn')(x)
x = Activation('relu', name='block1_conv1_act')(x)
x = Conv2D(64, 3, 3, bias=False, name='block1_conv2')(x)
x = BatchNormalization(name='block1_conv2_bn')(x)
x = Activation('relu', name='block1_conv2_act')(x)
residual = Conv2D(128, 1, 1, subsample=(2, 2),
border_mode='same', bias=False)(x)
residual = BatchNormalization()(residual)
x = SeparableConv2D(128, 3, 3, border_mode='same', bias=False, name='block2_sepconv1')(x)
x = BatchNormalization(name='block2_sepconv1_bn')(x)
x = Activation('relu', name='block2_sepconv2_act')(x)
x = SeparableConv2D(128, 3, 3, border_mode='same', bias=False, name='block2_sepconv2')(x)
x = BatchNormalization(name='block2_sepconv2_bn')(x)
x = MaxPooling2D((3, 3), strides=(2, 2), border_mode='same', name='block2_pool')(x)
x = merge([x, residual], mode='sum')
residual = Conv2D(256, 1, 1, subsample=(2, 2),
border_mode='same', bias=False)(x)
residual = BatchNormalization()(residual)
x = Activation('relu', name='block3_sepconv1_act')(x)
x = SeparableConv2D(256, 3, 3, border_mode='same', bias=False, name='block3_sepconv1')(x)
x = BatchNormalization(name='block3_sepconv1_bn')(x)
x = Activation('relu', name='block3_sepconv2_act')(x)
x = SeparableConv2D(256, 3, 3, border_mode='same', bias=False, name='block3_sepconv2')(x)
x = BatchNormalization(name='block3_sepconv2_bn')(x)
x = MaxPooling2D((3, 3), strides=(2, 2), border_mode='same', name='block3_pool')(x)
x = merge([x, residual], mode='sum')
residual = Conv2D(728, 1, 1, subsample=(2, 2),
border_mode='same', bias=False)(x)
residual = BatchNormalization()(residual)
x = Activation('relu', name='block4_sepconv1_act')(x)
x = SeparableConv2D(728, 3, 3, border_mode='same', bias=False, name='block4_sepconv1')(x)
x = BatchNormalization(name='block4_sepconv1_bn')(x)
x = Activation('relu', name='block4_sepconv2_act')(x)
x = SeparableConv2D(728, 3, 3, border_mode='same', bias=False, name='block4_sepconv2')(x)
x = BatchNormalization(name='block4_sepconv2_bn')(x)
x = MaxPooling2D((3, 3), strides=(2, 2), border_mode='same', name='block4_pool')(x)
x = merge([x, residual], mode='sum')
for i in range(8):
residual = x
prefix = 'block' + str(i + 5)
x = Activation('relu', name=prefix + '_sepconv1_act')(x)
x = SeparableConv2D(728, 3, 3, border_mode='same', bias=False, name=prefix + '_sepconv1')(x)
x = BatchNormalization(name=prefix + '_sepconv1_bn')(x)
x = Activation('relu', name=prefix + '_sepconv2_act')(x)
x = SeparableConv2D(728, 3, 3, border_mode='same', bias=False, name=prefix + '_sepconv2')(x)
x = BatchNormalization(name=prefix + '_sepconv2_bn')(x)
x = Activation('relu', name=prefix + '_sepconv3_act')(x)
x = SeparableConv2D(728, 3, 3, border_mode='same', bias=False, name=prefix + '_sepconv3')(x)
x = BatchNormalization(name=prefix + '_sepconv3_bn')(x)
x = merge([x, residual], mode='sum')
residual = Conv2D(1024, 1, 1, subsample=(2, 2),
border_mode='same', bias=False)(x)
residual = BatchNormalization()(residual)
x = Activation('relu', name='block13_sepconv1_act')(x)
x = SeparableConv2D(728, 3, 3, border_mode='same', bias=False, name='block13_sepconv1')(x)
x = BatchNormalization(name='block13_sepconv1_bn')(x)
x = Activation('relu', name='block13_sepconv2_act')(x)
x = SeparableConv2D(1024, 3, 3, border_mode='same', bias=False, name='block13_sepconv2')(x)
x = BatchNormalization(name='block13_sepconv2_bn')(x)
x = MaxPooling2D((3, 3), strides=(2, 2), border_mode='same', name='block13_pool')(x)
x = merge([x, residual], mode='sum')
x = SeparableConv2D(1536, 3, 3, border_mode='same', bias=False, name='block14_sepconv1')(x)
x = BatchNormalization(name='block14_sepconv1_bn')(x)
x = Activation('relu', name='block14_sepconv1_act')(x)
x = SeparableConv2D(2048, 3, 3, border_mode='same', bias=False, name='block14_sepconv2')(x)
x = BatchNormalization(name='block14_sepconv2_bn')(x)
x = Activation('relu', name='block14_sepconv2_act')(x)
if include_top:
x = GlobalAveragePooling2D(name='avg_pool')(x)
x = Dense(1000, activation='softmax', name='predictions')(x)
# Create model
model = Model(img_input, x)
# load weights
if weights == 'imagenet':
if include_top:
weights_path = get_file('xception_weights_tf_dim_ordering_tf_kernels.h5',
TF_WEIGHTS_PATH,
cache_subdir='models')
else:
weights_path = get_file('xception_weights_tf_dim_ordering_tf_kernels_notop.h5',
TF_WEIGHTS_PATH_NO_TOP,
cache_subdir='models')
model.load_weights(weights_path)
if old_dim_ordering:
K.set_image_dim_ordering(old_dim_ordering)
return model
def nn_base(input_tensor=None, trainable=False):
# Determine proper input shape
if K.image_dim_ordering() == 'th':
input_shape = (3, None, None)
else:
input_shape = (None, None, 3)
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
if not K.is_keras_tensor(input_tensor):
img_input = Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
if K.image_dim_ordering() == 'tf':
bn_axis = 3
else:
bn_axis = 1
# for testing..
alpha = 1
depth_multiplier = 1
first_block_filters = _make_divisible(32 * alpha, 8)
channel_axis = 1 if K.image_data_format() == 'channels_first' else -1
# need this layer to pass the input image size
x = layers.ZeroPadding2D(padding=correct_pad(K, img_input, 3),
name='Conv1_pad')(img_input)
x = layers.Conv2D(first_block_filters,
kernel_size=3,
strides=(2, 2),
padding='valid',
use_bias=False,
name='Conv1')(x)
x = layers.BatchNormalization(axis=channel_axis,
epsilon=1e-3,
momentum=0.999,
name='bn_Conv1')(x)
x = layers.ReLU(6., name='Conv1_relu')(x)
x = _inverted_res_block(x,
filters=16,
alpha=alpha,
stride=1,
expansion=1,
block_id=0)
x = _inverted_res_block(x,
filters=24,
alpha=alpha,
stride=2,
expansion=6,
block_id=1)
x = _inverted_res_block(x,
filters=24,
alpha=alpha,
stride=1,
expansion=6,
block_id=2)
x = _inverted_res_block(x,
filters=32,
alpha=alpha,
stride=2,
expansion=6,
block_id=3)
x = _inverted_res_block(x,
filters=32,
alpha=alpha,
stride=1,
expansion=6,
block_id=4)
x = _inverted_res_block(x,
filters=32,
alpha=alpha,
stride=1,
expansion=6,
block_id=5)
x = _inverted_res_block(x,
filters=64,
alpha=alpha,
stride=2,
expansion=6,
block_id=6)
x = _inverted_res_block(x,
filters=64,
alpha=alpha,
stride=1,
expansion=6,
block_id=7)
x = _inverted_res_block(x,
filters=64,
alpha=alpha,
stride=1,
expansion=6,
block_id=8)
x = _inverted_res_block(x,
filters=64,
alpha=alpha,
stride=1,
expansion=6,
block_id=9)
x = _inverted_res_block(x,
filters=96,
alpha=alpha,
stride=1,
expansion=6,
block_id=10)
x = _inverted_res_block(x,
filters=96,
alpha=alpha,
stride=1,
expansion=6,
block_id=11)
x = _inverted_res_block(x,
filters=96,
alpha=alpha,
stride=1,
expansion=6,
block_id=12)
x = _inverted_res_block(x,
filters=160,
alpha=alpha,
stride=1,
expansion=6,
block_id=13)
x = _inverted_res_block(x,
filters=160,
alpha=alpha,
stride=1,
expansion=6,
block_id=14)
x = _inverted_res_block(x,
filters=160,
alpha=alpha,
stride=1,
expansion=6,
block_id=15)
x = _inverted_res_block(x,
filters=320,
alpha=alpha,
stride=1,
expansion=6,
block_id=16)
return x
def ResNet50(include_top=True, weights='imagenet',
input_tensor=None, bn_mode = 0):
'''Instantiate the ResNet50 architecture,
optionally loading weights pre-trained
on ImageNet. Note that when using TensorFlow,
for best performance you should set
`image_dim_ordering="tf"` in your Keras config
at ~/.keras/keras.json.
The model and the weights are compatible with both
TensorFlow and Theano. The dimension ordering
convention used by the model is the one
specified in your Keras config file.
# Arguments
include_top: whether to include the 3 fully-connected
layers at the top of the network.
weights: one of `None` (random initialization)
or "imagenet" (pre-training on ImageNet).
input_tensor: optional Keras tensor (i.e. xput of `layers.Input()`)
to use as image input for the model.
bn_mode: default 0, the mode for BatchNormalization
# Returns
A Keras model instance.
'''
if weights not in {'imagenet', None}:
raise ValueError('The `weights` argument should be either '
'`None` (random initialization) or `imagenet` '
'(pre-training on ImageNet).')
# Determine proper input shape
if K.image_dim_ordering() == 'th':
if include_top:
input_shape = (3, 224, 224)
else:
input_shape = (3, None, None)
else:
if include_top:
input_shape = (224, 224, 3)
else:
input_shape = (None, None, 3)
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
if not K.is_keras_tensor(input_tensor):
img_input = Input(tensor=input_tensor)
else:
img_input = input_tensor
if K.image_dim_ordering() == 'tf':
bn_axis = 3
else:
bn_axis = 1
x = ZeroPadding2D((3, 3))(img_input)
x = Convolution2D(64, 7, 7, subsample=(2, 2), name='conv1')(x)
x = BatchNormalization(axis=bn_axis, name='bn_conv1', mode=bn_mode)(x)
x = Activation('relu')(x)
x = MaxPooling2D((3, 3), strides=(2, 2))(x)
x = conv_block(x, 3, [64, 64, 256], stage=2, block='a', strides=(1, 1), bn_mode=bn_mode)
x = identity_block(x, 3, [64, 64, 256], stage=2, block='b', bn_mode=bn_mode)
x = identity_block(x, 3, [64, 64, 256], stage=2, block='c', bn_mode=bn_mode)
x = conv_block(x, 3, [128, 128, 512], stage=3, block='a', bn_mode=bn_mode)
x = identity_block(x, 3, [128, 128, 512], stage=3, block='b', bn_mode=bn_mode)
x = identity_block(x, 3, [128, 128, 512], stage=3, block='c', bn_mode=bn_mode)
x = identity_block(x, 3, [128, 128, 512], stage=3, block='d', bn_mode=bn_mode)
x = conv_block(x, 3, [256, 256, 1024], stage=4, block='a', bn_mode=bn_mode)
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='b', bn_mode=bn_mode)
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='c', bn_mode=bn_mode)
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='d', bn_mode=bn_mode)
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='e', bn_mode=bn_mode)
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='f', bn_mode=bn_mode)
x = conv_block(x, 3, [512, 512, 2048], stage=5, block='a', bn_mode=bn_mode)
x = identity_block(x, 3, [512, 512, 2048], stage=5, block='b', bn_mode=bn_mode)
x = identity_block(x, 3, [512, 512, 2048], stage=5, block='c', bn_mode=bn_mode)
x = AveragePooling2D((7, 7), name='avg_pool')(x)
if include_top:
x = Flatten()(x)
x = Dense(1000, activation='softmax', name='fc1000')(x)
model = Model(img_input, x)
# load weights
if weights == 'imagenet':
print('K.image_dim_ordering:', K.image_dim_ordering())
if K.image_dim_ordering() == 'th':
if include_top:
weights_path = get_file('resnet50_weights_th_dim_ordering_th_kernels.h5',
TH_WEIGHTS_PATH,
cache_subdir='models',
md5_hash='1c1f8f5b0c8ee28fe9d950625a230e1c')
else:
weights_path = get_file('resnet50_weights_th_dim_ordering_th_kernels_notop.h5',
TH_WEIGHTS_PATH_NO_TOP,
cache_subdir='models',
md5_hash='f64f049c92468c9affcd44b0976cdafe')
model.load_weights(weights_path)
if K.backend() == 'tensorflow':
warnings.warn('You are using the TensorFlow backend, yet you '
'are using the Theano '
'image dimension ordering convention '
'(`image_dim_ordering="th"`). '
'For best performance, set '
'`image_dim_ordering="tf"` in '
'your Keras config '
'at ~/.keras/keras.json.')
convert_all_kernels_in_model(model)
else:
if include_top:
weights_path = get_file('resnet50_weights_tf_dim_ordering_tf_kernels.h5',
TF_WEIGHTS_PATH,
cache_subdir='models',
md5_hash='a7b3fe01876f51b976af0dea6bc144eb')
else:
weights_path = get_file('resnet50_weights_tf_dim_ordering_tf_kernels_notop.h5',
TF_WEIGHTS_PATH_NO_TOP,
cache_subdir='models',
md5_hash='a268eb855778b3df3c7506639542a6af')
model.load_weights(weights_path)
if K.backend() == 'theano':
convert_all_kernels_in_model(model)
return model
def DenseNet(input_shape=None,
depth=40,
nb_dense_block=3,
growth_rate=12,
nb_filter=-1,
nb_layers_per_block=-1,
bottleneck=False,
reduction=0.0,
dropout_rate=0.0,
weight_decay=1e-4,
subsample_initial_block=False,
include_top=True,
weights=None,
input_tensor=None,
classes=10,
activation='softmax'):
'''Instantiate the DenseNet architecture,
optionally loading weights pre-trained
on CIFAR-10. Note that when using TensorFlow,
for best performance you should set
`image_data_format='channels_last'` in your Keras config
at ~/.keras/keras.json.
The model and the weights are compatible with both
TensorFlow and Theano. The dimension ordering
convention used by the model is the one
specified in your Keras config file.
# Arguments
input_shape: optional shape tuple, only to be specified
if `include_top` is False (otherwise the input shape
has to be `(32, 32, 3)` (with `channels_last` dim ordering)
or `(3, 32, 32)` (with `channels_first` dim ordering).
It should have exactly 3 inputs channels,
and width and height should be no smaller than 8.
E.g. `(200, 200, 3)` would be one valid value.
depth: number or layers in the DenseNet
nb_dense_block: number of dense blocks to add to end (generally = 3)
growth_rate: number of filters to add per dense block
nb_filter: initial number of filters. -1 indicates initial
number of filters is 2 * growth_rate
nb_layers_per_block: number of layers in each dense block.
Can be a -1, positive integer or a list.
If -1, calculates nb_layer_per_block from the network depth.
If positive integer, a set number of layers per dense block.
If list, nb_layer is used as provided. Note that list size must
be (nb_dense_block + 1)
bottleneck: flag to add bottleneck blocks in between dense blocks
reduction: reduction factor of transition blocks.
Note : reduction value is inverted to compute compression.
dropout_rate: dropout rate
weight_decay: weight decay rate
subsample_initial_block: Set to True to subsample the initial convolution and
add a MaxPool2D before the dense blocks are added.
include_top: whether to include the fully-connected
layer at the top of the network.
weights: one of `None` (random initialization) or
'imagenet' (pre-training on ImageNet)..
input_tensor: optional Keras tensor (i.e. output of `layers.Input()`)
to use as image input for the model.
classes: optional number of classes to classify images
into, only to be specified if `include_top` is True, and
if no `weights` argument is specified.
activation: Type of activation at the top layer. Can be one of 'softmax' or 'sigmoid'.
Note that if sigmoid is used, classes must be 1.
# Returns
A Keras model instance.
'''
if weights not in {'imagenet', None}:
raise ValueError('The `weights` argument should be either '
'`None` (random initialization) or `cifar10` '
'(pre-training on CIFAR-10).')
if weights == 'imagenet' and include_top and classes != 1000:
raise ValueError('If using `weights` as ImageNet with `include_top`'
' as true, `classes` should be 1000')
if activation not in ['softmax', 'sigmoid']:
raise ValueError('activation must be one of "softmax" or "sigmoid"')
if activation == 'sigmoid' and classes != 1:
raise ValueError(
'sigmoid activation can only be used when classes = 1')
# Determine proper input shape
input_shape = _obtain_input_shape(input_shape,
default_size=32,
min_size=8,
data_format=K.image_data_format(),
require_flatten=include_top)
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
if not K.is_keras_tensor(input_tensor):
img_input = Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
x = __create_dense_net(classes, img_input, include_top, depth,
nb_dense_block, growth_rate, nb_filter,
nb_layers_per_block, bottleneck, reduction,
dropout_rate, weight_decay, subsample_initial_block,
activation)
# Ensure that the model takes into account
# any potential predecessors of `input_tensor`.
from keras.engine.topology import get_source_inputs
from keras.utils.data_utils import get_file
if input_tensor is not None:
inputs = get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model.
model = Model(inputs, x, name='densenet')
# load weights
if weights == 'imagenet':
weights_loaded = False
if (depth == 121) and (nb_dense_block == 4) and (growth_rate == 32) and (nb_filter == 64) and \
(bottleneck is True) and (reduction == 0.5) and (dropout_rate == 0.0) and (subsample_initial_block):
if include_top:
weights_path = get_file(
'DenseNet-BC-121-32.h5',
DENSENET_121_WEIGHTS_PATH,
cache_subdir='models',
md5_hash='a439dd41aa672aef6daba4ee1fd54abd')
else:
weights_path = get_file(
'DenseNet-BC-121-32-no-top.h5',
DENSENET_121_WEIGHTS_PATH_NO_TOP,
cache_subdir='models',
md5_hash='55e62a6358af8a0af0eedf399b5aea99')
model.load_weights(weights_path)
weights_loaded = True
if (depth == 161) and (nb_dense_block == 4) and (growth_rate == 48) and (nb_filter == 96) and \
(bottleneck is True) and (reduction == 0.5) and (dropout_rate == 0.0) and (subsample_initial_block):
if include_top:
weights_path = get_file(
'DenseNet-BC-161-48.h5',
DENSENET_161_WEIGHTS_PATH,
cache_subdir='models',
md5_hash='6c326cf4fbdb57d31eff04333a23fcca')
else:
weights_path = get_file(
'DenseNet-BC-161-48-no-top.h5',
DENSENET_161_WEIGHTS_PATH_NO_TOP,
cache_subdir='models',
md5_hash='1a9476b79f6b7673acaa2769e6427b92')
model.load_weights(weights_path)
weights_loaded = True
if (depth == 169) and (nb_dense_block == 4) and (growth_rate == 32) and (nb_filter == 64) and \
(bottleneck is True) and (reduction == 0.5) and (dropout_rate == 0.0) and (subsample_initial_block):
if include_top:
weights_path = get_file(
'DenseNet-BC-169-32.h5',
DENSENET_169_WEIGHTS_PATH,
cache_subdir='models',
md5_hash='914869c361303d2e39dec640b4e606a6')
else:
weights_path = get_file(
'DenseNet-BC-169-32-no-top.h5',
DENSENET_169_WEIGHTS_PATH_NO_TOP,
cache_subdir='models',
md5_hash='89c19e8276cfd10585d5fadc1df6859e')
model.load_weights(weights_path)
weights_loaded = True
if weights_loaded:
if K.backend() == 'theano':
convert_all_kernels_in_model(model)
if K.image_data_format() == 'channels_first' and K.backend(
) == 'tensorflow':
warnings.warn('You are using the TensorFlow backend, yet you '
'are using the Theano '
'image data format convention '
'(`image_data_format="channels_first"`). '
'For best performance, set '
'`image_data_format="channels_last"` in '
'your Keras config '
'at ~/.keras/keras.json.')
print("Weights for the model were loaded successfully")
return model
def InceptionV3SameSwish(include_top=True,
weights='imagenet',
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000):
"""Instantiates the Inception v3 architecture.
Optionally loads weights pre-trained
on ImageNet. Note that when using TensorFlow,
for best performance you should set
`image_data_format='channels_last'` in your Keras config
at ~/.keras/keras.json.
The model and the weights are compatible with both
TensorFlow and Theano. The data format
convention used by the model is the one
specified in your Keras config file.
Note that the default input image size for this model is 299x299.
# Arguments
include_top: whether to include the fully-connected
layer at the top of the network.
weights: one of `None` (random initialization),
'imagenet' (pre-training on ImageNet),
or the path to the weights file to be loaded.
input_tensor: optional Keras tensor (i.e. output of `layers.Input()`)
to use as image input for the model.
input_shape: optional shape tuple, only to be specified
if `include_top` is False (otherwise the input shape
has to be `(299, 299, 3)` (with `channels_last` data format)
or `(3, 299, 299)` (with `channels_first` data format).
It should have exactly 3 inputs channels,
and width and height should be no smaller than 139.
E.g. `(150, 150, 3)` would be one valid value.
pooling: Optional pooling mode for feature extraction
when `include_top` is `False`.
- `None` means that the output of the model will be
the 4D tensor output of the
last convolutional layer.
- `avg` means that global average pooling
will be applied to the output of the
last convolutional layer, and thus
the output of the model will be a 2D tensor.
- `max` means that global max pooling will
be applied.
classes: optional number of classes to classify images
into, only to be specified if `include_top` is True, and
if no `weights` argument is specified.
# Returns
A Keras model instance.
# Raises
ValueError: in case of invalid argument for `weights`,
or invalid input shape.
"""
if not (weights in {'imagenet', None} or os.path.exists(weights)):
raise ValueError('The `weights` argument should be either '
'`None` (random initialization), `imagenet` '
'(pre-training on ImageNet), '
'or the path to the weights file to be loaded.')
if weights == 'imagenet' and include_top and classes != 1000:
raise ValueError('If using `weights` as imagenet with `include_top`'
' as true, `classes` should be 1000')
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
if not K.is_keras_tensor(input_tensor):
img_input = Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
if K.image_data_format() == 'channels_first':
channel_axis = 1
else:
channel_axis = 3
x = conv2d_bn(img_input, 32, 3, 3, strides=(2, 2), padding='same')
x = conv2d_bn(x, 32, 3, 3, padding='same')
x = conv2d_bn(x, 64, 3, 3)
x = MaxPooling2D((3, 3), strides=(2, 2), padding='same')(x)
x = conv2d_bn(x, 80, 1, 1, padding='same')
x = conv2d_bn(x, 192, 3, 3, padding='same')
x = MaxPooling2D((3, 3), strides=(2, 2), padding='same')(x)
# mixed 0, 1, 2: 35 x 35 x 256
branch1x1 = conv2d_bn(x, 64, 1, 1)
branch5x5 = conv2d_bn(x, 48, 1, 1)
branch5x5 = conv2d_bn(branch5x5, 64, 5, 5)
branch3x3dbl = conv2d_bn(x, 64, 1, 1)
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3)
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3)
branch_pool = AveragePooling2D((3, 3), strides=(1, 1), padding='same')(x)
branch_pool = conv2d_bn(branch_pool, 32, 1, 1)
x = layers.concatenate(
[branch1x1, branch5x5, branch3x3dbl, branch_pool],
axis=channel_axis,
name='mixed0')
# mixed 1: 35 x 35 x 256
branch1x1 = conv2d_bn(x, 64, 1, 1)
branch5x5 = conv2d_bn(x, 48, 1, 1)
branch5x5 = conv2d_bn(branch5x5, 64, 5, 5)
branch3x3dbl = conv2d_bn(x, 64, 1, 1)
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3)
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3)
branch_pool = AveragePooling2D((3, 3), strides=(1, 1), padding='same')(x)
branch_pool = conv2d_bn(branch_pool, 64, 1, 1)
x = layers.concatenate(
[branch1x1, branch5x5, branch3x3dbl, branch_pool],
axis=channel_axis,
name='mixed1')
# mixed 2: 35 x 35 x 256
branch1x1 = conv2d_bn(x, 64, 1, 1)
branch5x5 = conv2d_bn(x, 48, 1, 1)
branch5x5 = conv2d_bn(branch5x5, 64, 5, 5)
branch3x3dbl = conv2d_bn(x, 64, 1, 1)
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3)
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3)
branch_pool = AveragePooling2D((3, 3), strides=(1, 1), padding='same')(x)
branch_pool = conv2d_bn(branch_pool, 64, 1, 1)
x = layers.concatenate(
[branch1x1, branch5x5, branch3x3dbl, branch_pool],
axis=channel_axis,
name='mixed2')
# mixed 3: 17 x 17 x 768
branch3x3 = conv2d_bn(x, 384, 3, 3, strides=(2, 2), padding='same')
branch3x3dbl = conv2d_bn(x, 64, 1, 1)
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3)
branch3x3dbl = conv2d_bn(
branch3x3dbl, 96, 3, 3, strides=(2, 2), padding='same')
branch_pool = MaxPooling2D((3, 3), strides=(2, 2), padding='same')(x)
x = layers.concatenate(
[branch3x3, branch3x3dbl, branch_pool], axis=channel_axis, name='mixed3')
# mixed 4: 17 x 17 x 768
branch1x1 = conv2d_bn(x, 192, 1, 1)
branch7x7 = conv2d_bn(x, 128, 1, 1)
branch7x7 = conv2d_bn(branch7x7, 128, 1, 7)
branch7x7 = conv2d_bn(branch7x7, 192, 7, 1)
branch7x7dbl = conv2d_bn(x, 128, 1, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 128, 7, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 128, 1, 7)
branch7x7dbl = conv2d_bn(branch7x7dbl, 128, 7, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 1, 7)
branch_pool = AveragePooling2D((3, 3), strides=(1, 1), padding='same')(x)
branch_pool = conv2d_bn(branch_pool, 192, 1, 1)
x = layers.concatenate(
[branch1x1, branch7x7, branch7x7dbl, branch_pool],
axis=channel_axis,
name='mixed4')
# mixed 5, 6: 17 x 17 x 768
for i in range(2):
branch1x1 = conv2d_bn(x, 192, 1, 1)
branch7x7 = conv2d_bn(x, 160, 1, 1)
branch7x7 = conv2d_bn(branch7x7, 160, 1, 7)
branch7x7 = conv2d_bn(branch7x7, 192, 7, 1)
branch7x7dbl = conv2d_bn(x, 160, 1, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 160, 7, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 160, 1, 7)
branch7x7dbl = conv2d_bn(branch7x7dbl, 160, 7, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 1, 7)
branch_pool = AveragePooling2D(
(3, 3), strides=(1, 1), padding='same')(x)
branch_pool = conv2d_bn(branch_pool, 192, 1, 1)
x = layers.concatenate(
[branch1x1, branch7x7, branch7x7dbl, branch_pool],
axis=channel_axis,
name='mixed' + str(5 + i))
# mixed 7: 17 x 17 x 768
branch1x1 = conv2d_bn(x, 192, 1, 1)
branch7x7 = conv2d_bn(x, 192, 1, 1)
branch7x7 = conv2d_bn(branch7x7, 192, 1, 7)
branch7x7 = conv2d_bn(branch7x7, 192, 7, 1)
branch7x7dbl = conv2d_bn(x, 192, 1, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 7, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 1, 7)
branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 7, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 1, 7)
branch_pool = AveragePooling2D((3, 3), strides=(1, 1), padding='same')(x)
branch_pool = conv2d_bn(branch_pool, 192, 1, 1)
x = layers.concatenate(
[branch1x1, branch7x7, branch7x7dbl, branch_pool],
axis=channel_axis,
name='mixed7')
# mixed 8: 8 x 8 x 1280
branch3x3 = conv2d_bn(x, 192, 1, 1)
branch3x3 = conv2d_bn(branch3x3, 320, 3, 3,
strides=(2, 2), padding='same')
branch7x7x3 = conv2d_bn(x, 192, 1, 1)
branch7x7x3 = conv2d_bn(branch7x7x3, 192, 1, 7)
branch7x7x3 = conv2d_bn(branch7x7x3, 192, 7, 1)
branch7x7x3 = conv2d_bn(
branch7x7x3, 192, 3, 3, strides=(2, 2), padding='same')
branch_pool = MaxPooling2D((3, 3), strides=(2, 2), padding='same')(x)
x = layers.concatenate(
[branch3x3, branch7x7x3, branch_pool], axis=channel_axis, name='mixed8')
# mixed 9: 8 x 8 x 2048
for i in range(2):
branch1x1 = conv2d_bn(x, 320, 1, 1)
branch3x3 = conv2d_bn(x, 384, 1, 1)
branch3x3_1 = conv2d_bn(branch3x3, 384, 1, 3)
branch3x3_2 = conv2d_bn(branch3x3, 384, 3, 1)
branch3x3 = layers.concatenate(
[branch3x3_1, branch3x3_2], axis=channel_axis, name='mixed9_' + str(i))
branch3x3dbl = conv2d_bn(x, 448, 1, 1)
branch3x3dbl = conv2d_bn(branch3x3dbl, 384, 3, 3)
branch3x3dbl_1 = conv2d_bn(branch3x3dbl, 384, 1, 3)
branch3x3dbl_2 = conv2d_bn(branch3x3dbl, 384, 3, 1)
branch3x3dbl = layers.concatenate(
[branch3x3dbl_1, branch3x3dbl_2], axis=channel_axis)
branch_pool = AveragePooling2D(
(3, 3), strides=(1, 1), padding='same')(x)
branch_pool = conv2d_bn(branch_pool, 192, 1, 1)
x = layers.concatenate(
[branch1x1, branch3x3, branch3x3dbl, branch_pool],
axis=channel_axis,
name='mixed' + str(9 + i))
if include_top:
# Classification block
x = GlobalAveragePooling2D(name='avg_pool')(x)
x = Dense(classes, activation='softmax', name='predictions')(x)
else:
if pooling == 'avg':
x = GlobalAveragePooling2D()(x)
elif pooling == 'max':
x = GlobalMaxPooling2D()(x)
# Ensure that the model takes into account
# any potential predecessors of `input_tensor`.
if input_tensor is not None:
inputs = get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model.
model = Model(inputs, x, name='inception_v3')
# load weights
if weights == 'imagenet':
if K.image_data_format() == 'channels_first':
if K.backend() == 'tensorflow':
warnings.warn('You are using the TensorFlow backend, yet you '
'are using the Theano '
'image data format convention '
'(`image_data_format="channels_first"`). '
'For best performance, set '
'`image_data_format="channels_last"` in '
'your Keras config '
'at ~/.keras/keras.json.')
if include_top:
weights_path = get_file(
'inception_v3_weights_tf_dim_ordering_tf_kernels.h5',
WEIGHTS_PATH,
cache_subdir='models',
file_hash='9a0d58056eeedaa3f26cb7ebd46da564')
else:
weights_path = get_file(
'inception_v3_weights_tf_dim_ordering_tf_kernels_notop.h5',
WEIGHTS_PATH_NO_TOP,
cache_subdir='models',
file_hash='bcbd6486424b2319ff4ef7d526e38f63')
if input_shape[-1] > 3:
conv1 = model.get_layer('conv2d_1')
conv1.name = 'conv1_more_channels'
model.load_weights(weights_path, by_name=True)
if input_shape[-1] > 3:
print("Loading weights for conv1 layer separately for the first 3 channels")
conv1_weights = np.zeros((3, 3, input_shape[-1], 32), dtype="float32")
inception_ori = InceptionV3(include_top=False, input_shape=(299, 299, 3))
conv1_weights[:, :, :3, :] = inception_ori.layers[1].get_weights()[0][:, :, :, :]
# random init
conv1_weights[:, :, 3:, :] = model.get_layer('conv1_more_channels').get_weights()[0][:, :, 3:, :]
model.get_layer('conv1_more_channels').set_weights((conv1_weights,))
model.get_layer('conv1_more_channels').name = 'conv2d_1'
elif weights is not None:
model.load_weights(weights)
return model
def sklearnAUC(test_labels, test_prediction):
K.print_tensor(test_labels)
print(K.is_keras_tensor(test_labels), K.shape(test_labels))
K.print_tensor(test_prediction)
print(K.is_keras_tensor(test_prediction), K.shape(test_prediction))
return K.mean(test_prediction)
def SparseNet(input_shape=None, depth=40, nb_dense_block=3, growth_rate=12, nb_filter=-1, nb_layers_per_block=-1,
bottleneck=False, reduction=0.0, dropout_rate=0.0, weight_decay=1e-4, subsample_initial_block=False,
include_top=True, weights=None, input_tensor=None,
classes=10, activation='softmax'):
'''Instantiate the SparseNet architecture,
optionally loading weights pre-trained
on CIFAR-10. Note that when using TensorFlow,
for best performance you should set
`image_data_format='channels_last'` in your Keras config
at ~/.keras/keras.json.
The model and the weights are compatible with both
TensorFlow and Theano. The dimension ordering
convention used by the model is the one
specified in your Keras config file.
# Arguments
input_shape: optional shape tuple, only to be specified
if `include_top` is False (otherwise the input shape
has to be `(32, 32, 3)` (with `channels_last` dim ordering)
or `(3, 32, 32)` (with `channels_first` dim ordering).
It should have exactly 3 inputs channels,
and width and height should be no smaller than 8.
E.g. `(200, 200, 3)` would be one valid value.
depth: number or layers in the DenseNet
nb_dense_block: number of dense blocks to add to end (generally = 3)
growth_rate: number of filters to add per dense block. Can be
a single integer number or a list of numbers.
If it is a list, length of list must match the length of
`nb_layers_per_block`
nb_filter: initial number of filters. -1 indicates initial
number of filters is 2 * growth_rate
nb_layers_per_block: number of layers in each dense block.
Can be a -1, positive integer or a list.
If -1, calculates nb_layer_per_block from the network depth.
If positive integer, a set number of layers per dense block.
If list, nb_layer is used as provided. Note that list size must
be (nb_dense_block + 1)
bottleneck: flag to add bottleneck blocks in between dense blocks
reduction: reduction factor of transition blocks.
Note : reduction value is inverted to compute compression.
dropout_rate: dropout rate
weight_decay: weight decay rate
subsample_initial_block: Set to True to subsample the initial convolution and
add a MaxPool2D before the dense blocks are added.
include_top: whether to include the fully-connected
layer at the top of the network.
weights: one of `None` (random initialization) or
'imagenet' (pre-training on ImageNet)..
input_tensor: optional Keras tensor (i.e. output of `layers.Input()`)
to use as image input for the model.
classes: optional number of classes to classify images
into, only to be specified if `include_top` is True, and
if no `weights` argument is specified.
activation: Type of activation at the top layer. Can be one of 'softmax' or 'sigmoid'.
Note that if sigmoid is used, classes must be 1.
# Returns
A Keras model instance.
'''
if weights not in {'imagenet', None}:
raise ValueError('The `weights` argument should be either '
'`None` (random initialization) or `cifar10` '
'(pre-training on CIFAR-10).')
if weights == 'imagenet' and include_top and classes != 1000:
raise ValueError('If using `weights` as ImageNet with `include_top`'
' as true, `classes` should be 1000')
if activation not in ['softmax', 'sigmoid']:
raise ValueError('activation must be one of "softmax" or "sigmoid"')
if activation == 'sigmoid' and classes != 1:
raise ValueError('sigmoid activation can only be used when classes = 1')
# Determine proper input shape
input_shape = _obtain_input_shape(input_shape,
default_size=32,
min_size=8,
data_format=K.image_data_format(),
require_flatten=include_top)
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
if not K.is_keras_tensor(input_tensor):
img_input = Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
x = _create_dense_net(classes, img_input, include_top, depth, nb_dense_block,
growth_rate, nb_filter, nb_layers_per_block, bottleneck, reduction,
dropout_rate, weight_decay, subsample_initial_block, activation)
# Ensure that the model takes into account
# any potential predecessors of `input_tensor`.
if input_tensor is not None:
inputs = get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model.
model = Model(inputs, x, name='densenet')
# load weights
if weights == 'imagenet':
weights_loaded = False
if weights_loaded:
if K.backend() == 'theano':
convert_all_kernels_in_model(model)
if K.image_data_format() == 'channels_first' and K.backend() == 'tensorflow':
warnings.warn('You are using the TensorFlow backend, yet you '
'are using the Theano '
'image data format convention '
'(`image_data_format="channels_first"`). '
'For best performance, set '
'`image_data_format="channels_last"` in '
'your Keras config '
'at ~/.keras/keras.json.')
print("Weights for the model were loaded successfully")
return model
def default_classification_model(input_shape=None,
input_tensor=None,
num_classes=7,
num_dense_layers=2,
num_dense_units=256,
dropout_rate=0.,
pooling=None,
use_output_activation=True,
kernel_regularizer=None):
"""
:param kernel_regularizer: l1 or l2 or none regularization
:param num_classes: # of classes to predict a score for each feature level.
:param input_shape: Input shape
:param input_tensor: Input tensor
:param num_dense_layers: Number of dense layers before the output layer
:param num_dense_units: The number of filters to use in the layers in the classification submodel.
:param dropout_rate: Dropout Rate
:param pooling: which pooling to use at conv output
:param use_output_activation: whether to use output activation
:return: A keras.model.Model that predicts class
"""
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
if not K.is_keras_tensor(input_tensor):
img_input = Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
assert kernel_regularizer in [None, 'L1', 'L2', 'L1-L2'], \
'Unknown regularizer %s' % kernel_regularizer
if kernel_regularizer == 'L1':
kernel_regularizer = regularizers.l1(1e-4)
elif kernel_regularizer == 'L2':
kernel_regularizer = regularizers.l2(1e-3)
elif kernel_regularizer == 'L1-L2':
kernel_regularizer = regularizers.l1_l2(l1=1e-4, l2=1e-3)
assert pooling in {None, 'avg', 'max',
'flatten'}, 'Unknown pooling option %s' % pooling
if pooling == 'avg':
outputs = keras.layers.GlobalAveragePooling2D(
name='avg_pool_our')(img_input)
elif pooling == 'max':
outputs = keras.layers.GlobalMaxPooling2D(
name='max_pool_our')(img_input)
else:
outputs = keras.layers.Flatten(name='flatten_our')(img_input)
if dropout_rate > 0.:
outputs = keras.layers.Dropout(rate=dropout_rate,
name='drop_5')(outputs, training=True)
for i in range(num_dense_layers):
outputs = keras.layers.Dense(
num_dense_units,
activation='relu',
name='fc%d' % (i + 1),
kernel_regularizer=kernel_regularizer)(outputs)
if dropout_rate > 0.:
outputs = keras.layers.Dropout(rate=dropout_rate,
name='drop_6')(outputs,
training=True)
outputs = keras.layers.Dense(
num_classes, name='predictions',
kernel_regularizer=kernel_regularizer)(outputs)
if use_output_activation:
activation = 'sigmoid' if num_classes == 1 else 'softmax'
outputs = keras.layers.Activation(activation, name='outputs')(outputs)
return outputs
def ResNet50(include_top=True, weights='imagenet',
input_tensor=None, input_shape=None,
pooling=None,
classes=1000):
"""Instantiates the ResNet50 architecture.
Optionally loads weights pre-trained
on ImageNet. Note that when using TensorFlow,
for best performance you should set
`image_data_format="channels_last"` in your Keras config
at ~/.keras/keras.json.
The model and the weights are compatible with both
TensorFlow and Theano. The data format
convention used by the model is the one
specified in your Keras config file.
# Arguments
include_top: whether to include the fully-connected
layer at the top of the network.
weights: one of `None` (random initialization)
or "imagenet" (pre-training on ImageNet).
input_tensor: optional Keras tensor (i.e. output of `layers.Input()`)
to use as image input for the model.
input_shape: optional shape tuple, only to be specified
if `include_top` is False (otherwise the input shape
has to be `(224, 224, 3)` (with `channels_last` data format)
or `(3, 224, 244)` (with `channels_first` data format).
It should have exactly 3 inputs channels,
and width and height should be no smaller than 197.
E.g. `(200, 200, 3)` would be one valid value.
pooling: Optional pooling mode for feature extraction
when `include_top` is `False`.
- `None` means that the output of the model will be
the 4D tensor output of the
last convolutional layer.
- `avg` means that global average pooling
will be applied to the output of the
last convolutional layer, and thus
the output of the model will be a 2D tensor.
- `max` means that global max pooling will
be applied.
classes: optional number of classes to classify images
into, only to be specified if `include_top` is True, and
if no `weights` argument is specified.
# Returns
A Keras model instance.
# Raises
ValueError: in case of invalid argument for `weights`,
or invalid input shape.
"""
if weights not in {'imagenet', None}:
raise ValueError('The `weights` argument should be either '
'`None` (random initialization) or `imagenet` '
'(pre-training on ImageNet).')
if weights == 'imagenet' and include_top and classes != 1000:
raise ValueError('If using `weights` as imagenet with `include_top`'
' as true, `classes` should be 1000')
# Determine proper input shape
input_shape = _obtain_input_shape(input_shape,
default_size=224,
min_size=197,
data_format=K.image_data_format(),
include_top=include_top)
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
if not K.is_keras_tensor(input_tensor):
img_input = Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
if K.image_data_format() == 'channels_last':
bn_axis = 3
else:
bn_axis = 1
x = ZeroPadding2D((3, 3))(img_input)
x = Conv2D(64, (7, 7), strides=(2, 2), name='conv1')(x)
x = BatchNormalization(axis=bn_axis, name='bn_conv1')(x)
x = Activation('relu')(x)
x = MaxPooling2D((3, 3), strides=(2, 2))(x)
x = conv_block(x, 3, [64, 64, 256], stage=2, block='a', strides=(1, 1))
x = identity_block(x, 3, [64, 64, 256], stage=2, block='b')
x = identity_block(x, 3, [64, 64, 256], stage=2, block='c')
x = conv_block(x, 3, [128, 128, 512], stage=3, block='a')
x = identity_block(x, 3, [128, 128, 512], stage=3, block='b')
x = identity_block(x, 3, [128, 128, 512], stage=3, block='c')
x = identity_block(x, 3, [128, 128, 512], stage=3, block='d')
x = conv_block(x, 3, [256, 256, 1024], stage=4, block='a')
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='b')
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='c')
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='d')
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='e')
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='f')
x = conv_block(x, 3, [512, 512, 2048], stage=5, block='a')
x = identity_block(x, 3, [512, 512, 2048], stage=5, block='b')
x = identity_block(x, 3, [512, 512, 2048], stage=5, block='c')
x = AveragePooling2D((7, 7), name='avg_pool')(x)
if include_top:
x = Flatten()(x)
x = Dense(classes, activation='softmax', name='fc1000')(x)
else:
if pooling == 'avg':
x = GlobalAveragePooling2D()(x)
elif pooling == 'max':
x = GlobalMaxPooling2D()(x)
# Ensure that the model takes into account
# any potential predecessors of `input_tensor`.
if input_tensor is not None:
inputs = get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model.
model = Model(inputs, x, name='resnet50')
# load weights
if weights == 'imagenet':
if include_top:
weights_path = get_file('resnet50_weights_tf_dim_ordering_tf_kernels.h5',
WEIGHTS_PATH,
cache_subdir='models',
md5_hash='a7b3fe01876f51b976af0dea6bc144eb')
else:
weights_path = get_file('resnet50_weights_tf_dim_ordering_tf_kernels_notop.h5',
WEIGHTS_PATH_NO_TOP,
cache_subdir='models',
md5_hash='a268eb855778b3df3c7506639542a6af')
model.load_weights(weights_path)
if K.backend() == 'theano':
layer_utils.convert_all_kernels_in_model(model)
if K.image_data_format() == 'channels_first':
if include_top:
maxpool = model.get_layer(name='avg_pool')
shape = maxpool.output_shape[1:]
dense = model.get_layer(name='fc1000')
layer_utils.convert_dense_weights_data_format(dense, shape, 'channels_first')
if K.backend() == 'tensorflow':
warnings.warn('You are using the TensorFlow backend, yet you '
'are using the Theano '
'image data format convention '
'(`image_data_format="channels_first"`). '
'For best performance, set '
'`image_data_format="channels_last"` in '
'your Keras config '
'at ~/.keras/keras.json.')
return model
def build_sis(self, input_tensor=None, OS=16):
""" Instantiates the Deeplabv3+ architecture
Optionally loads pretrained_weights pre-trained
on PASCAL VOC. This model is available for TensorFlow only,
and can only be used with inputs following the TensorFlow
data format `(width, height, channels)`.
# Arguments
pretrained_weights: one of 'pascal_voc' (pre-trained on pascal voc)
or None (random initialization)
input_tensor: optional Keras tensor (i.e. output of `layers.Input()`)
to use as image input for the model.
img_shape: shape of input image. format HxWxC
PASCAL VOC model was trained on (512,512,3) images
classes: number of desired classes. If classes != 21,
last layer is initialized randomly
OS: determines img_shape/feature_extractor_output ratio. One of {8,16}.
Used only for xception backbone.
# Returns
A Keras model instance.
# Raises
RuntimeError: If attempting to run this model with a
backend that does not support separable convolutions.
ValueError: in case of invalid argument for `pretrained_weights` or `backbone`
"""
def SepConv_BN(x,
filters,
prefix,
stride=1,
kernel_size=3,
rate=1,
depth_activation=False,
epsilon=1e-3):
""" SepConv with BN between depthwise & pointwise. Optionally add activation after BN
Implements right "same" padding for even kernel sizes
Args:
x: input tensor
filters: num of filters in pointwise convolution
prefix: prefix before name
stride: stride at depthwise conv
kernel_size: kernel size for depthwise convolution
rate: atrous rate for depthwise convolution
depth_activation: flag to use activation between depthwise & poinwise convs
epsilon: epsilon to use in BN layer
"""
if stride == 1:
depth_padding = 'same'
else:
kernel_size_effective = kernel_size + (kernel_size -
1) * (rate - 1)
pad_total = kernel_size_effective - 1
pad_beg = pad_total // 2
pad_end = pad_total - pad_beg
x = ZeroPadding2D((pad_beg, pad_end))(x)
depth_padding = 'valid'
if not depth_activation:
x = Activation('relu')(x)
x = DepthwiseConv2D((kernel_size, kernel_size),
strides=(stride, stride),
dilation_rate=(rate, rate),
padding=depth_padding,
use_bias=False,
name=prefix + '_depthwise')(x)
x = BatchNormalization(name=prefix + '_depthwise_BN',
epsilon=epsilon)(x)
if depth_activation:
x = Activation('relu')(x)
x = Conv2D(filters, (1, 1),
padding='same',
use_bias=False,
name=prefix + '_pointwise')(x)
x = BatchNormalization(name=prefix + '_pointwise_BN',
epsilon=epsilon)(x)
if depth_activation:
x = Activation('relu')(x)
return x
def _conv2d_same(x, filters, prefix, stride=1, kernel_size=3, rate=1):
"""Implements right 'same' padding for even kernel sizes
Without this there is a 1 pixel drift when stride = 2
Args:
x: input tensor
filters: num of filters in pointwise convolution
prefix: prefix before name
stride: stride at depthwise conv
kernel_size: kernel size for depthwise convolution
rate: atrous rate for depthwise convolution
"""
if stride == 1:
return Conv2D(filters, (kernel_size, kernel_size),
strides=(stride, stride),
padding='same',
use_bias=False,
dilation_rate=(rate, rate),
name=prefix)(x)
else:
kernel_size_effective = kernel_size + (kernel_size -
1) * (rate - 1)
pad_total = kernel_size_effective - 1
pad_beg = pad_total // 2
pad_end = pad_total - pad_beg
x = ZeroPadding2D((pad_beg, pad_end))(x)
return Conv2D(filters, (kernel_size, kernel_size),
strides=(stride, stride),
padding='valid',
use_bias=False,
dilation_rate=(rate, rate),
name=prefix)(x)
def _xception_block(inputs,
depth_list,
prefix,
skip_connection_type,
stride,
rate=1,
depth_activation=False,
return_skip=False):
""" Basic building block of modified Xception network
Args:
inputs: input tensor
depth_list: number of filters in each SepConv layer. len(depth_list) == 3
prefix: prefix before name
skip_connection_type: one of {'conv','sum','none'}
stride: stride at last depthwise conv
rate: atrous rate for depthwise convolution
depth_activation: flag to use activation between depthwise & pointwise convs
return_skip: flag to return additional tensor after 2 SepConvs for decoder
"""
residual = inputs
for i in range(3):
residual = SepConv_BN(residual,
depth_list[i],
prefix +
'_separable_conv{}'.format(i + 1),
stride=stride if i == 2 else 1,
rate=rate,
depth_activation=depth_activation)
if i == 1:
skip = residual
if skip_connection_type == 'conv':
shortcut = _conv2d_same(inputs,
depth_list[-1],
prefix + '_shortcut',
kernel_size=1,
stride=stride)
shortcut = BatchNormalization(name=prefix +
'_shortcut_BN')(shortcut)
outputs = layers.add([residual, shortcut])
elif skip_connection_type == 'sum':
outputs = layers.add([residual, inputs])
elif skip_connection_type == 'none':
outputs = residual
if return_skip:
return outputs, skip
else:
return outputs
def _make_divisible(v, divisor, min_value=None):
if min_value is None:
min_value = divisor
new_v = max(min_value, int(v + divisor / 2) // divisor * divisor)
# Make sure that round down does not go down by more than 10%.
if new_v < 0.9 * v:
new_v += divisor
return new_v
if not (self.pretrained_weights in {'pascal_voc', None}):
raise ValueError(
'The `pretrained_weights` argument should be either '
'`None` (random initialization) or `pascal_voc` '
'(pre-trained on PASCAL VOC)')
if input_tensor is None:
img_input = Input(shape=self.img_shape)
else:
if not K.is_keras_tensor(input_tensor):
img_input = Input(tensor=input_tensor, shape=self.img_shape)
else:
img_input = input_tensor
if OS == 8:
entry_block3_stride = 1
middle_block_rate = 2 # ! Not mentioned in paper, but required
exit_block_rates = (2, 4)
atrous_rates = (12, 24, 36)
else:
entry_block3_stride = 2
middle_block_rate = 1
exit_block_rates = (1, 2)
atrous_rates = (6, 12, 18)
x = Conv2D(32, (3, 3),
strides=(2, 2),
name='entry_flow_conv1_1',
use_bias=False,
padding='same')(img_input)
x = BatchNormalization(name='entry_flow_conv1_1_BN')(x)
x = Activation('relu')(x)
x = _conv2d_same(x, 64, 'entry_flow_conv1_2', kernel_size=3, stride=1)
x = BatchNormalization(name='entry_flow_conv1_2_BN')(x)
x = Activation('relu')(x)
x = _xception_block(x, [128, 128, 128],
'entry_flow_block1',
skip_connection_type='conv',
stride=2,
depth_activation=False)
x, skip1 = _xception_block(x, [256, 256, 256],
'entry_flow_block2',
skip_connection_type='conv',
stride=2,
depth_activation=False,
return_skip=True)
x = _xception_block(x, [728, 728, 728],
'entry_flow_block3',
skip_connection_type='conv',
stride=entry_block3_stride,
depth_activation=False)
for i in range(16):
x = _xception_block(x, [728, 728, 728],
'middle_flow_unit_{}'.format(i + 1),
skip_connection_type='sum',
stride=1,
rate=middle_block_rate,
depth_activation=False)
x = _xception_block(x, [728, 1024, 1024],
'exit_flow_block1',
skip_connection_type='conv',
stride=1,
rate=exit_block_rates[0],
depth_activation=False)
x = _xception_block(x, [1536, 1536, 2048],
'exit_flow_block2',
skip_connection_type='none',
stride=1,
rate=exit_block_rates[1],
depth_activation=True)
# end of feature extractor
# branching for Atrous Spatial Pyramid Pooling
# Image Feature branch
#out_shape = int(np.ceil(img_shape[0] / OS))
b4 = AveragePooling2D(pool_size=(int(np.ceil(self.img_shape[0] / OS)),
int(np.ceil(self.img_shape[1] /
OS))))(x)
b4 = Conv2D(256, (1, 1),
padding='same',
use_bias=False,
name='image_pooling')(b4)
b4 = BatchNormalization(name='image_pooling_BN', epsilon=1e-5)(b4)
b4 = Activation('relu')(b4)
b4 = BilinearUpsampling((int(np.ceil(self.img_shape[0] / OS)),
int(np.ceil(self.img_shape[1] / OS))))(b4)
# simple 1x1
b0 = Conv2D(256, (1, 1), padding='same', use_bias=False,
name='aspp0')(x)
b0 = BatchNormalization(name='aspp0_BN', epsilon=1e-5)(b0)
b0 = Activation('relu', name='aspp0_activation')(b0)
# rate = 6 (12)
b1 = SepConv_BN(x,
256,
'aspp1',
rate=atrous_rates[0],
depth_activation=True,
epsilon=1e-5)
# rate = 12 (24)
b2 = SepConv_BN(x,
256,
'aspp2',
rate=atrous_rates[1],
depth_activation=True,
epsilon=1e-5)
# rate = 18 (36)
b3 = SepConv_BN(x,
256,
'aspp3',
rate=atrous_rates[2],
depth_activation=True,
epsilon=1e-5)
# concatenate ASPP branches & project
x = Concatenate()([b4, b0, b1, b2, b3])
x = Conv2D(256, (1, 1),
padding='same',
use_bias=False,
name='concat_projection')(x)
x = BatchNormalization(name='concat_projection_BN', epsilon=1e-5)(x)
x = Activation('relu')(x)
x = Dropout(0.1)(x)
# DeepLab v.3+ decoder
# Feature projection
# x4 (x2) block
x = BilinearUpsampling(
output_size=(int(np.ceil(self.img_shape[0] / 4)),
int(np.ceil(self.img_shape[1] / 4))))(x)
dec_skip1 = Conv2D(48, (1, 1),
padding='same',
use_bias=False,
name='feature_projection0')(skip1)
dec_skip1 = BatchNormalization(name='feature_projection0_BN',
epsilon=1e-5)(dec_skip1)
dec_skip1 = Activation('relu')(dec_skip1)
x = Concatenate()([x, dec_skip1])
x = SepConv_BN(x,
256,
'decoder_conv0',
depth_activation=True,
epsilon=1e-5)
x = SepConv_BN(x,
256,
'decoder_conv1',
depth_activation=True,
epsilon=1e-5)
# you can use it with arbitary number of classes
if self.classes == 21:
last_layer_name = 'logits_semantic'
else:
last_layer_name = 'custom_logits_semantic'
x = Conv2D(self.classes, (1, 1), padding='same',
name=last_layer_name)(x)
x = BilinearUpsampling(output_size=(self.img_shape[0],
self.img_shape[1]))(x)
# Ensure that the model takes into account
# any potential predecessors of `input_tensor`.
if input_tensor is not None:
inputs = get_source_inputs(input_tensor)
else:
inputs = img_input
self.sis = Model(inputs, x, name='deeplabv3plus')
self.sis.summary()
plot_model(self.sis,
to_file="sis_plot.png",
show_layer_names=True,
show_shapes=True)
# load pretrained_weights
if self.pretrained_weights != None:
self.sis.load_weights(cwd + self.pretrained_weights, by_name=True)
return
def SENET50(include_top=True, weights='vggface',
input_tensor=None, input_shape=None,
pooling=None,
classes=8631):
input_shape = _obtain_input_shape(input_shape,
default_size=224,
min_size=197,
data_format=K.image_data_format(),
require_flatten=include_top,
weights=weights)
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
if not K.is_keras_tensor(input_tensor):
img_input = Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
if K.image_data_format() == 'channels_last':
bn_axis = 3
else:
bn_axis = 1
x = Conv2D(
64, (7, 7), use_bias=False, strides=(2, 2), padding='same',
name='conv1/7x7_s2')(img_input)
x = BatchNormalization(axis=bn_axis, name='conv1/7x7_s2/bn')(x)
x = Activation('relu')(x)
x = MaxPooling2D((3, 3), strides=(2, 2))(x)
x = senet_conv_block(x, 3, [64, 64, 256], stage=2, block=1, strides=(1, 1))
x = senet_identity_block(x, 3, [64, 64, 256], stage=2, block=2)
x = senet_identity_block(x, 3, [64, 64, 256], stage=2, block=3)
x = senet_conv_block(x, 3, [128, 128, 512], stage=3, block=1)
x = senet_identity_block(x, 3, [128, 128, 512], stage=3, block=2)
x = senet_identity_block(x, 3, [128, 128, 512], stage=3, block=3)
x = senet_identity_block(x, 3, [128, 128, 512], stage=3, block=4)
x = senet_conv_block(x, 3, [256, 256, 1024], stage=4, block=1)
x = senet_identity_block(x, 3, [256, 256, 1024], stage=4, block=2)
x = senet_identity_block(x, 3, [256, 256, 1024], stage=4, block=3)
x = senet_identity_block(x, 3, [256, 256, 1024], stage=4, block=4)
x = senet_identity_block(x, 3, [256, 256, 1024], stage=4, block=5)
x = senet_identity_block(x, 3, [256, 256, 1024], stage=4, block=6)
x = senet_conv_block(x, 3, [512, 512, 2048], stage=5, block=1)
x = senet_identity_block(x, 3, [512, 512, 2048], stage=5, block=2)
x = senet_identity_block(x, 3, [512, 512, 2048], stage=5, block=3)
x = AveragePooling2D((7, 7), name='avg_pool')(x)
if include_top:
x = Flatten()(x)
x = Dense(classes, activation='softmax', name='classifier')(x)
else:
if pooling == 'avg':
x = GlobalAveragePooling2D()(x)
elif pooling == 'max':
x = GlobalMaxPooling2D()(x)
# Ensure that the model takes into account
# any potential predecessors of `input_tensor`.
if input_tensor is not None:
inputs = get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model.
model = Model(inputs, x, name='vggface_senet50')
# load weights
if weights == 'vggface':
if include_top:
weights_path = get_file('rcmalli_vggface_tf_senet50.h5',
utils.SENET50_WEIGHTS_PATH,
cache_subdir=utils.VGGFACE_DIR)
else:
weights_path = get_file('rcmalli_vggface_tf_notop_senet50.h5',
utils.SENET50_WEIGHTS_PATH_NO_TOP,
cache_subdir=utils.VGGFACE_DIR)
model.load_weights(weights_path)
if K.backend() == 'theano':
layer_utils.convert_all_kernels_in_model(model)
if include_top:
maxpool = model.get_layer(name='avg_pool')
shape = maxpool.output_shape[1:]
dense = model.get_layer(name='classifier')
layer_utils.convert_dense_weights_data_format(dense, shape,
'channels_first')
if K.image_data_format() == 'channels_first' and K.backend() == 'tensorflow':
warnings.warn('You are using the TensorFlow backend, yet you '
'are using the Theano '
'image data format convention '
'(`image_data_format="channels_first"`). '
'For best performance, set '
'`image_data_format="channels_last"` in '
'your Keras config '
'at ~/.keras/keras.json.')
elif weights is not None:
model.load_weights(weights)
return model
def InceptionResNetV1(include_top=True,
weights='facenet',
input_tensor=None,
input_shape=None,
pooling=None,
classes=44051,
dropout_keep_prob=0.8):
"""Instantiates the Inception-ResNet v2 architecture.
Optionally loads weights pre-trained on ImageNet.
Note that when using TensorFlow, for best performance you should
set `"image_data_format": "channels_last"` in your Keras config
at `~/.keras/keras.json`.
The model and the weights are compatible with both TensorFlow and Theano.
The data format convention used by the model is the one specified in your
Keras config file.
Note that the default input image size for this model is 299x299, instead
of 224x224 as in the VGG16 and ResNet models. Also, the input preprocessing
function is different (i.e., do not use `imagenet_utils.preprocess_input()`
with this model. Use `preprocess_input()` defined in this module instead).
# Arguments
include_top: whether to include the fully-connected
layer at the top of the network.
weights: one of `None` (random initialization)
or `'imagenet'` (pre-training on ImageNet).
input_tensor: optional Keras tensor (i.e. output of `layers.Input()`)
to use as image input for the model.
input_shape: optional shape tuple, only to be specified
if `include_top` is `False` (otherwise the input shape
has to be `(299, 299, 3)` (with `channels_last` data format)
or `(3, 299, 299)` (with `channels_first` data format).
It should have exactly 3 inputs channels,
and width and height should be no smaller than 139.
E.g. `(150, 150, 3)` would be one valid value.
pooling: Optional pooling mode for feature extraction
when `include_top` is `False`.
- `None` means that the output of the model will be
the 4D tensor output of the last convolutional layer.
- `'avg'` means that global average pooling
will be applied to the output of the
last convolutional layer, and thus
the output of the model will be a 2D tensor.
- `'max'` means that global max pooling will be applied.
classes: optional number of classes to classify images
into, only to be specified if `include_top` is `True`, and
if no `weights` argument is specified.
dropout_keep_prob: dropout keep rate after pooling and before the
classification layer, only to be specified if `include_top` is `True`.
# Returns
A Keras `Model` instance.
# Raises
ValueError: in case of invalid argument for `weights`,
or invalid input shape.
"""
if weights not in {'facent', None}:
raise ValueError('The `weights` argument should be either '
'`None` (random initialization) or `facent` '
'(pre-training on ImageNet).')
if weights == 'facent' and include_top and classes != 44051:
raise ValueError('If using `weights` as facent with `include_top`'
' as true, `classes` should be 44051')
# Determine proper input shape
input_shape = _obtain_input_shape(input_shape,
default_size=299,
min_size=139,
data_format=K.image_data_format(),
require_flatten=False,
weights=weights)
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
if not K.is_keras_tensor(input_tensor):
img_input = Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
# Stem block: 35 x 35 x 192
x = conv2d_bn(img_input,
32,
3,
strides=2,
padding='valid',
name='Conv2d_1a_3x3')
print("TOP1:", x._keras_shape)
x = conv2d_bn(x, 32, 3, padding='valid', name='Conv2d_2a_3x3')
print("TOP2:", x._keras_shape)
x = conv2d_bn(x, 64, 3, name='Conv2d_2b_3x3')
print("TOP3:", x._keras_shape)
x = MaxPooling2D(3, strides=2, name='MaxPool_3a_3x3')(x)
print("TOP4:", x._keras_shape)
x = conv2d_bn(x, 80, 1, padding='valid', name='Conv2d_3b_1x1')
print("TOP5:", x._keras_shape)
x = conv2d_bn(x, 192, 3, padding='valid', name='Conv2d_4a_3x3')
print("TOP6:", x._keras_shape)
#----->
x = conv2d_bn(x, 256, 3, strides=2, padding='valid', name='Conv2d_4b_3x3')
print("TOP5:35 x 35 x 256:", x._keras_shape)
# 5x Block35 (Inception-ResNet-A block): 35 x 35 x 320
# 5x Inception-resnet-A
for block_idx in range(1, 6):
x = _inception_resnet_block(x,
scale=0.17,
block_type='Block35',
block_idx=block_idx)
print("TOP6:", x._keras_shape)
# Mixed 6a (Reduction-A block): 17 x 17 x 1088
channel_axis = 1 if K.image_data_format() == 'channels_first' else 3
name_fmt = partial(_generate_layer_name, prefix='Mixed_6a')
branch_0 = conv2d_bn(x,
384,
3,
strides=2,
padding='valid',
name=name_fmt('Conv2d_1a_3x3', 0))
branch_1 = conv2d_bn(x, 192, 1, name=name_fmt('Conv2d_0a_1x1', 1))
branch_1 = conv2d_bn(branch_1, 192, 3, name=name_fmt('Conv2d_0b_3x3', 1))
branch_1 = conv2d_bn(branch_1,
256,
3,
strides=2,
padding='valid',
name=name_fmt('Conv2d_1a_3x3', 1))
branch_pool = MaxPooling2D(3,
strides=2,
padding='valid',
name=name_fmt('MaxPool_1a_3x3', 2))(x)
branches = [branch_0, branch_1, branch_pool]
x = Concatenate(axis=channel_axis, name='Mixed_6a')(branches)
print("TOP7:", x._keras_shape)
# 10x Block17 (Inception-ResNet-B block): 17 x 17 x 1088
for block_idx in range(1, 11):
x = _inception_resnet_block(x,
scale=0.1,
block_type='Block17',
block_idx=block_idx)
print("TOP8:", x._keras_shape)
# Mixed 7a (Reduction-B block): 8 x 8 x 2080
name_fmt = partial(_generate_layer_name, prefix='Mixed_7a')
branch_0 = conv2d_bn(x, 256, 1, name=name_fmt('Conv2d_0a_1x1', 0))
branch_0 = conv2d_bn(branch_0,
384,
3,
strides=2,
padding='valid',
name=name_fmt('Conv2d_1a_3x3', 0))
branch_1 = conv2d_bn(x, 256, 1, name=name_fmt('Conv2d_0a_1x1', 1))
branch_1 = conv2d_bn(branch_1,
256,
3,
strides=2,
padding='valid',
name=name_fmt('Conv2d_1a_3x3', 1))
branch_2 = conv2d_bn(x, 256, 1, name=name_fmt('Conv2d_0a_1x1', 2))
branch_2 = conv2d_bn(branch_2, 256, 3, name=name_fmt('Conv2d_0b_3x3', 2))
branch_2 = conv2d_bn(branch_2,
256,
3,
strides=2,
padding='valid',
name=name_fmt('Conv2d_1a_3x3', 2))
branch_pool = MaxPooling2D(3,
strides=2,
padding='valid',
name=name_fmt('MaxPool_1a_3x3', 3))(x)
branches = [branch_0, branch_1, branch_2, branch_pool]
x = Concatenate(axis=channel_axis, name='Mixed_7a')(branches)
print("TOP9:", x._keras_shape)
# 5x Block8 (Inception-ResNet-C block): 8 x 8 x 2080
for block_idx in range(1, 6):
x = _inception_resnet_block(x,
scale=0.2,
block_type='Block8',
block_idx=block_idx)
print("TOP0:", x._keras_shape)
x = _inception_resnet_block(x,
scale=1.,
activation=None,
block_type='Block8',
block_idx=6)
print("TOP1:", x._keras_shape)
# Final convolution block
#x = conv2d_bn(x, 128, 1, strides=2, use_bias=False, padding='valid', name='Bottleneck', activation=None)
#----->
if include_top:
# Classification block
#x = GlobalAveragePooling2D(name='avg_pool')(x)
#x = Dense(classes, activation='softmax', name='predictions')(x)
x = GlobalAveragePooling2D(name='AvgPool')(x)
x = Dropout(1.0 - dropout_keep_prob, name='Dropout')(x)
x = Dense(classes, name='Logits')(x)
x = Activation('softmax', name='Predictions')(x)
print("TOP-a:", x._keras_shape)
else:
if pooling == 'avg':
x = GlobalAveragePooling2D(name='AvgPool')(x)
elif pooling == 'max':
x = GlobalMaxPooling2D(name='MaxPool')(x)
print("TOP-b:", x._keras_shape)
print("TOP2:", x._keras_shape)
# Ensure that the model takes into account
# any potential predecessors of `input_tensor`
if input_tensor is not None:
inputs = get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model
model = Model(inputs, x, name='inception_resnet_v1')
# Load weights
if weights == 'facenet':
if K.image_data_format() == 'channels_first':
if K.backend() == 'tensorflow':
warnings.warn('You are using the TensorFlow backend, yet you '
'are using the Theano '
'image data format convention '
'(`image_data_format="channels_first"`). '
'For best performance, set '
'`image_data_format="channels_last"` in '
'your Keras config '
'at ~/.keras/keras.json.')
if include_top:
weights_filename = 'inception_resnet_v1_weights_tf_dim_ordering_tf_kernels.h5'
weights_path = get_file(
weights_filename,
BASE_WEIGHT_URL + weights_filename,
cache_subdir='models',
md5_hash='b183cf243925b74bac6d617a5dc1293d')
else:
weights_filename = 'inception_resnet_v1_weights_tf_dim_ordering_tf_kernels_notop.h5'
weights_path = get_file(
weights_filename,
BASE_WEIGHT_URL + weights_filename,
cache_subdir='models',
md5_hash='9126ac1e7f4274c03399923b6b6e6d44')
model.load_weights(weights_path)
return model
def MobileNetV2(input_shape=None,
alpha=1.0,
depth_multiplier=1,
include_top=True,
weights='imagenet',
input_tensor=None,
classes=1000):
"""Instantiates the MobileNetV2 architecture.
To load a MobileNetV2 model via `load_model`, import the custom
objects `relu6` and pass them to the `custom_objects` parameter.
E.g.
model = load_model('mobilenet.h5', custom_objects={
'relu6': mobilenet.relu6})
# Arguments
input_shape: optional shape tuple, to be specified if you would
like to use a model with an input img resolution that is not
(224, 224, 3).
It should have exactly 3 inputs channels (224, 224, 3).
You can also omit this option if you would like
to infer input_shape from an input_tensor.
If you choose to include both input_tensor and input_shape then
input_shape will be used if they match, if the shapes
do not match then we will throw an error.
E.g. `(160, 160, 3)` would be one valid value.
alpha: controls the width of the network. This is known as the
width multiplier in the MobileNetV2 paper.
- If `alpha` < 1.0, proportionally decreases the number
of filters in each layer.
- If `alpha` > 1.0, proportionally increases the number
of filters in each layer.
- If `alpha` = 1, default number of filters from the paper
are used at each layer.
depth_multiplier: depth multiplier for depthwise convolution
(also called the resolution multiplier)
include_top: whether to include the fully-connected
layer at the top of the network.
weights: one of `None` (random initialization),
'imagenet' (pre-training on ImageNet),
or the path to the weights file to be loaded.
input_tensor: optional Keras tensor (i.e. output of
`layers.Input()`)
to use as image input for the model.
classes: optional number of classes to classify images
into, only to be specified if `include_top` is True, and
if no `weights` argument is specified.
# Returns
A Keras model instance.
# Raises
ValueError: in case of invalid argument for `weights`,
or invalid input shape or invalid depth_multiplier, alpha,
rows when weights='imagenet'
"""
if not (weights in {'imagenet', None} or os.path.exists(weights)):
raise ValueError('The `weights` argument should be either '
'`None` (random initialization), `imagenet` '
'(pre-training on ImageNet), '
'or the path to the weights file to be loaded.')
if weights == 'imagenet' and include_top and classes != 1000:
raise ValueError('If using `weights` as ImageNet with `include_top` '
'as true, `classes` should be 1000')
# Determine proper input shape and default size.
# If both input_shape and input_tensor are used, they should match
if input_shape is not None and input_tensor is not None:
try:
is_input_t_tensor = K.is_keras_tensor(input_tensor)
except ValueError:
try:
is_input_t_tensor = K.is_keras_tensor(
get_source_inputs(input_tensor))
except ValueError:
raise ValueError('input_tensor: ', input_tensor,
'is not type input_tensor')
if is_input_t_tensor:
if K.image_data_format == 'channels_first':
if input_tensor._keras_shape[1] != input_shape[1]:
raise ValueError('input_shape: ', input_shape,
'and input_tensor: ', input_tensor,
'do not meet the same shape requirements')
else:
if input_tensor._keras_shape[2] != input_shape[1]:
raise ValueError('input_shape: ', input_shape,
'and input_tensor: ', input_tensor,
'do not meet the same shape requirements')
else:
raise ValueError('input_tensor specified: ', input_tensor,
'is not a keras tensor')
# If input_shape is None, infer shape from input_tensor
if input_shape is None and input_tensor is not None:
try:
K.is_keras_tensor(input_tensor)
except ValueError:
raise ValueError('input_tensor: ', input_tensor,
'is type: ', type(input_tensor),
'which is not a valid type')
if input_shape is None and not K.is_keras_tensor(input_tensor):
default_size = 224
elif input_shape is None and K.is_keras_tensor(input_tensor):
if K.image_data_format() == 'channels_first':
rows = input_tensor._keras_shape[2]
cols = input_tensor._keras_shape[3]
else:
rows = input_tensor._keras_shape[1]
cols = input_tensor._keras_shape[2]
if rows == cols and rows in [96, 128, 160, 192, 224]:
default_size = rows
else:
default_size = 224
# If input_shape is None and no input_tensor
elif input_shape is None:
default_size = 224
# If input_shape is not None, assume default size
else:
if K.image_data_format() == 'channels_first':
rows = input_shape[1]
cols = input_shape[2]
else:
rows = input_shape[0]
cols = input_shape[1]
if rows == cols and rows in [96, 128, 160, 192, 224]:
default_size = rows
else:
default_size = 224
input_shape = _obtain_input_shape(input_shape,
default_size=default_size,
min_size=32,
data_format=K.image_data_format(),
require_flatten=include_top,
weights=weights)
if K.image_data_format() == 'channels_last':
row_axis, col_axis = (0, 1)
else:
row_axis, col_axis = (1, 2)
rows = input_shape[row_axis]
cols = input_shape[col_axis]
if weights == 'imagenet':
if depth_multiplier != 1:
raise ValueError('If imagenet weights are being loaded, '
'depth multiplier must be 1')
if alpha not in [0.35, 0.50, 0.75, 1.0, 1.3, 1.4]:
raise ValueError('If imagenet weights are being loaded, '
'alpha can be one of'
'`0.25`, `0.50`, `0.75` or `1.0` only.')
if rows != cols or rows not in [96, 128, 160, 192, 224]:
if rows is None:
rows = 224
warnings.warn('MobileNet shape is undefined.'
' Weights for input shape'
'(224, 224) will be loaded.')
else:
raise ValueError('If imagenet weights are being loaded, '
'input must have a static square shape'
'(one of (96, 96), (128, 128), (160, 160),'
'(192, 192), or (224, 224)).'
'Input shape provided = %s' % (input_shape,))
if K.image_data_format() != 'channels_last':
warnings.warn('The MobileNet family of models is only available '
'for the input data format "channels_last" '
'(width, height, channels). '
'However your settings specify the default '
'data format "channels_first" (channels, width, height).'
' You should set `image_data_format="channels_last"` '
'in your Keras config located at ~/.keras/keras.json. '
'The model being returned right now will expect inputs '
'to follow the "channels_last" data format.')
K.set_image_data_format('channels_last')
old_data_format = 'channels_first'
else:
old_data_format = None
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
if not K.is_keras_tensor(input_tensor):
img_input = Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
first_block_filters = _make_divisible(32 * alpha, 8)
x = Conv2D(first_block_filters,
kernel_size=3,
strides=(2, 2), padding='same',
use_bias=False, name='Conv1')(img_input)
x = BatchNormalization(epsilon=1e-3, momentum=0.999, name='bn_Conv1')(x)
x = Activation(relu6, name='Conv1_relu')(x)
x = _first_inverted_res_block(x,
filters=16,
alpha=alpha,
stride=1,
expansion=1,
block_id=0)
x = _inverted_res_block(x, filters=24, alpha=alpha, stride=2,
expansion=6, block_id=1)
x = _inverted_res_block(x, filters=24, alpha=alpha, stride=1,
expansion=6, block_id=2)
x = _inverted_res_block(x, filters=32, alpha=alpha, stride=2,
expansion=6, block_id=3)
x = _inverted_res_block(x, filters=32, alpha=alpha, stride=1,
expansion=6, block_id=4)
x = _inverted_res_block(x, filters=32, alpha=alpha, stride=1,
expansion=6, block_id=5)
x = _inverted_res_block(x, filters=64, alpha=alpha, stride=2,
expansion=6, block_id=6)
x = _inverted_res_block(x, filters=64, alpha=alpha, stride=1,
expansion=6, block_id=7)
x = _inverted_res_block(x, filters=64, alpha=alpha, stride=1,
expansion=6, block_id=8)
x = _inverted_res_block(x, filters=64, alpha=alpha, stride=1,
expansion=6, block_id=9)
x = _inverted_res_block(x, filters=96, alpha=alpha, stride=1,
expansion=6, block_id=10)
x = _inverted_res_block(x, filters=96, alpha=alpha, stride=1,
expansion=6, block_id=11)
x = _inverted_res_block(x, filters=96, alpha=alpha, stride=1,
expansion=6, block_id=12)
x = _inverted_res_block(x, filters=160, alpha=alpha, stride=2,
expansion=6, block_id=13)
x = _inverted_res_block(x, filters=160, alpha=alpha, stride=1,
expansion=6, block_id=14)
x = _inverted_res_block(x, filters=160, alpha=alpha, stride=1,
expansion=6, block_id=15)
x = _inverted_res_block(x, filters=320, alpha=alpha, stride=1,
expansion=6, block_id=16)
# no alpha applied to last conv as stated in the paper:
# if the width multiplier is greater than 1 we
# increase the number of output channels
if alpha > 1.0:
last_block_filters = _make_divisible(1280 * alpha, 8)
else:
last_block_filters = 1280
x = Conv2D(last_block_filters,
kernel_size=1,
use_bias=False,
name='Conv_1')(x)
x = BatchNormalization(epsilon=1e-3, momentum=0.999, name='Conv_1_bn')(x)
x = Activation(relu6, name='out_relu')(x)
if include_top:
x = GlobalAveragePooling2D()(x)
x = Dense(classes, activation='softmax',
use_bias=True, name='Logits')(x)
# Ensure that the model takes into account
# any potential predecessors of `input_tensor`.
if input_tensor is not None:
inputs = get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model.
model = Model(inputs, x, name='mobilenetv2_%0.2f_%s' % (alpha, rows))
# load weights
if weights == 'imagenet':
if K.image_data_format() == 'channels_first':
raise ValueError('Weights for "channels_first" format '
'are not available.')
if include_top:
model_name = 'mobilenet_v2_weights_tf_dim_ordering_tf_kernels_' + \
str(alpha) + '_' + str(rows) + '.h5'
weigh_path = BASE_WEIGHT_PATH + model_name
weights_path = get_file(model_name, weigh_path,
cache_subdir='models')
else:
model_name = 'mobilenet_v2_weights_tf_dim_ordering_tf_kernels_' + \
str(alpha) + '_' + str(rows) + '_no_top' + '.h5'
weigh_path = BASE_WEIGHT_PATH + model_name
weights_path = get_file(model_name, weigh_path,
cache_subdir='models')
print("load weights from", weights_path)
model.load_weights(weights_path)
elif weights is not None:
model.load_weights(weights)
if old_data_format:
K.set_image_data_format(old_data_format)
return model
def get_dilation_model_cityscapes(input_shape, apply_softmax, input_tensor, classes):
if input_tensor is None:
model_in = Input(shape=input_shape)
else:
if not K.is_keras_tensor(input_tensor):
model_in = Input(tensor=input_tensor, shape=input_shape)
else:
model_in = input_tensor
h = Convolution2D(64, 3, 3, activation='relu', name='conv1_1')(model_in)
h = Convolution2D(64, 3, 3, activation='relu', name='conv1_2')(h)
h = MaxPooling2D(pool_size=(2, 2), strides=(2, 2), name='pool1')(h)
h = Convolution2D(128, 3, 3, activation='relu', name='conv2_1')(h)
h = Convolution2D(128, 3, 3, activation='relu', name='conv2_2')(h)
h = MaxPooling2D(pool_size=(2, 2), strides=(2, 2), name='pool2')(h)
h = Convolution2D(256, 3, 3, activation='relu', name='conv3_1')(h)
h = Convolution2D(256, 3, 3, activation='relu', name='conv3_2')(h)
h = Convolution2D(256, 3, 3, activation='relu', name='conv3_3')(h)
h = MaxPooling2D(pool_size=(2, 2), strides=(2, 2), name='pool3')(h)
h = Convolution2D(512, 3, 3, activation='relu', name='conv4_1')(h)
h = Convolution2D(512, 3, 3, activation='relu', name='conv4_2')(h)
h = Convolution2D(512, 3, 3, activation='relu', name='conv4_3')(h)
h = AtrousConvolution2D(512, 3, 3, atrous_rate=(2, 2), activation='relu', name='conv5_1')(h)
h = AtrousConvolution2D(512, 3, 3, atrous_rate=(2, 2), activation='relu', name='conv5_2')(h)
h = AtrousConvolution2D(512, 3, 3, atrous_rate=(2, 2), activation='relu', name='conv5_3')(h)
h = AtrousConvolution2D(4096, 7, 7, atrous_rate=(4, 4), activation='relu', name='fc6')(h)
h = Dropout(0.5, name='drop6')(h)
h = Convolution2D(4096, 1, 1, activation='relu', name='fc7')(h)
h = Dropout(0.5, name='drop7')(h)
h = Convolution2D(classes, 1, 1, name='final')(h)
h = ZeroPadding2D(padding=(1, 1))(h)
h = Convolution2D(classes, 3, 3, activation='relu', name='ctx_conv1_1')(h)
h = ZeroPadding2D(padding=(1, 1))(h)
h = Convolution2D(classes, 3, 3, activation='relu', name='ctx_conv1_2')(h)
h = ZeroPadding2D(padding=(2, 2))(h)
h = AtrousConvolution2D(classes, 3, 3, atrous_rate=(2, 2), activation='relu', name='ctx_conv2_1')(h)
h = ZeroPadding2D(padding=(4, 4))(h)
h = AtrousConvolution2D(classes, 3, 3, atrous_rate=(4, 4), activation='relu', name='ctx_conv3_1')(h)
h = ZeroPadding2D(padding=(8, 8))(h)
h = AtrousConvolution2D(classes, 3, 3, atrous_rate=(8, 8), activation='relu', name='ctx_conv4_1')(h)
h = ZeroPadding2D(padding=(16, 16))(h)
h = AtrousConvolution2D(classes, 3, 3, atrous_rate=(16, 16), activation='relu', name='ctx_conv5_1')(h)
h = ZeroPadding2D(padding=(32, 32))(h)
h = AtrousConvolution2D(classes, 3, 3, atrous_rate=(32, 32), activation='relu', name='ctx_conv6_1')(h)
h = ZeroPadding2D(padding=(64, 64))(h)
h = AtrousConvolution2D(classes, 3, 3, atrous_rate=(64, 64), activation='relu', name='ctx_conv7_1')(h)
h = ZeroPadding2D(padding=(1, 1))(h)
h = Convolution2D(classes, 3, 3, activation='relu', name='ctx_fc1')(h)
h = Convolution2D(classes, 1, 1, name='ctx_final')(h)
# the following two layers pretend to be a Deconvolution with grouping layer.
# never managed to implement it in Keras
# since it's just a gaussian upsampling trainable=False is recommended
h = UpSampling2D(size=(8, 8))(h)
logits = Convolution2D(classes, 16, 16, border_mode='same', bias=False, trainable=False, name='ctx_upsample')(h)
if apply_softmax:
model_out = softmax(logits)
else:
model_out = logits
model = Model(input=model_in, output=model_out, name='dilation_cityscapes')
return model
