def mDeeplab(weights='pascal_voc',
input_tensor=None,
input_shape=(320, 240, 3),
classes=1,
backbone='mobilenetv2',
OS=8,
alpha=0.5,
temp=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 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='Conv')(img_input)
x = BatchNormalization(epsilon=1e-3, momentum=0.999, name='Conv_BN')(x)
# x = Activation(relu6, name='Conv_Relu6')(x)
x = ReLU(6., 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=(40, 30))(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 = ReLU(6.)(b4)
# b4 = BilinearUpsampling((40,30))(b4)
# b4=K.tf.image.resize_bilinear(b4, (40,30),align_corners=True)
b4 = keras.layers.UpSampling2D((40, 30), interpolation='bilinear')(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)
b0 = ReLU()(b0)
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 = ReLU()(x)
x = Dropout(0.1)(x)
# DeepLab v.3+ decoder
x = Conv2D(classes, (1, 1), padding='same', name='custom')(x)
# x = BilinearUpsampling(output_size=(320,240))(x)
# x=K.tf.image.resize_bilinear(x, (320, 240), align_corners=True)
x = keras.layers.UpSampling2D((8, 8),
interpolation='bilinear',
name='logit_label')(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, name='main_input')
else:
inputs = img_input
soft_x = keras.layers.Lambda(lambda x: (1 / temp) * x)(x)
soft_x = keras.layers.Activation('sigmoid', name='soft')(soft_x)
x = keras.layers.Activation('sigmoid', name='stand')(x)
# input=keras.layers.Input(shape=(320,240,3),name='main_input')
model = Model(inputs=inputs, outputs=[soft_x, x])
# load weights
# model.load_weights('deeplabv3_mobilenetv2_tf_dim_ordering_tf_kernels.h5', by_name=True)
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 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))
shape_before = K.shape(x)
b4 = GlobalAveragePooling2D()(x)
b4 = K.expand_dims(tf.expand_dims(b4, 1),
1) # from (b_size, channels)->(b_size, 1, 1, channels)
#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 = Lambda(lambda x: K.resize(
x, shape_before[1:3], method='bilinear', align_corners=True))(
b4) #upsample
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='deeplabv3+')
# 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 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 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 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 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 CENet_ceshi(input_tensor=None, input_shape=None, pooling=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_64 = Conv2d_BN(img_input,nb_filter=64,kernel_size=(7,7),strides=(2,2),padding='same')
#(32,32,64)
x_32 = Conv_Block(x_64,nb_filter=64,kernel_size=(3,3),num = 3)
#(16,16,128)
x_16 = Conv_Block(x_32,nb_filter=128,kernel_size=(3,3),num = 4)
#(8,8,256)
x_8 = Conv_Block(x_16,nb_filter=256,kernel_size=(3,3),num = 6)
#(4,4,512)
x_4 = Conv_Block(x_8,nb_filter=512,kernel_size=(3,3),num = 3)
# #Dense Atrous Convolution module
x = Dense_Atrous_Convolution(x_4)
# #Residual Multi-kernel pooling
x = Residual_Multikernel_pooling(x)
#upsample
x = Conv2d_BN(x,nb_filter=512,kernel_size=(1,1),strides=(1,1),padding='same')
x = Conv2DTranspose(512,(3, 3),strides=(2, 2),padding='same')(x)
x = Conv2d_BN(x,nb_filter=512,kernel_size=(1,1),strides=(1,1),padding='same')
x = concatenate([x,x_8])
x = Conv2d_BN(x,nb_filter=256,kernel_size=(1,1),strides=(1,1),padding='same')
x = Conv2DTranspose(256,(3, 3),strides=(2, 2),padding='same')(x)
x = Conv2d_BN(x,nb_filter=256,kernel_size=(1,1),strides=(1,1),padding='same')
x = concatenate([x,x_16])
x = Conv2d_BN(x,nb_filter=128,kernel_size=(1,1),strides=(1,1),padding='same')
x = Conv2DTranspose(128,(3, 3),strides=(2, 2),padding='same')(x)
x = Conv2d_BN(x,nb_filter=128,kernel_size=(1,1),strides=(1,1),padding='same')
x = concatenate([x,x_32])
x = Conv2d_BN(x,nb_filter=64,kernel_size=(1,1),strides=(1,1),padding='same')
x = Conv2DTranspose(64,(3, 3),strides=(2, 2),padding='same')(x)
x = Conv2d_BN(x,nb_filter=64,kernel_size=(1,1),strides=(1,1),padding='same')
x = concatenate([x,x_64])
x = Conv2d_BN(x,nb_filter=64,kernel_size=(1,1),strides=(1,1),padding='same')
x = Conv2DTranspose(64,(3, 3),strides=(2, 2),padding='same')(x)
x = Conv2d_BN(x,nb_filter=64,kernel_size=(1,1),strides=(1,1),padding='same')
x = Conv2D(4, (1, 1), activation='sigmoid', padding='same')(x)
if input_tensor is not None:
inputs = get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model
model = Model(inputs , x, name='CENet_ceshi')
return model
def ResNet152(include_top=True,
weights=None,
input_tensor=None,
input_shape=None,
large_input=False,
pooling=None,
classes=257):
"""Instantiate the ResNet152 architecture.
Keyword arguments:
include_top -- whether to include the fully-connected layer at the
top of the network. (default True)
weights -- one of `None` (random initialization) or "imagenet"
(pre-training on ImageNet). (default None)
input_tensor -- optional Keras tensor (i.e. output of `layers.Input()`)
to use as image input for the model.(default None)
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 197. E.g. `(200, 200, 3)` would be one valid value.
(default None)
large_input -- if True, then the input shape expected will be
`(448, 448, 3)` (with `channels_last` data format) or
`(3, 448, 448)` (with `channels_first` data format). (default False)
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.
(default None)
classes -- optional number of classes to classify image into, only
to be specified if `include_top` is True, and if no `weights`
argument is specified. (default 1000)
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')
eps = 1.1e-5
if large_input:
img_size = 448
else:
img_size = 224
# Determine proper input shape
input_shape = obtain_input_shape(input_shape,
default_size=img_size,
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
# handle dimension ordering for different backends
if K.image_data_format() == 'channels_last':
bn_axis = 3
else:
bn_axis = 1
x = ZeroPadding2D((3, 3), name='conv1_zeropadding')(img_input)
x = Conv2D(64, (7, 7), strides=(2, 2), name='conv1', use_bias=False)(x)
x = BatchNormalization(epsilon=eps, axis=bn_axis, name='bn_conv1')(x)
x = Scale(axis=bn_axis, name='scale_conv1')(x)
x = Activation('relu', name='conv1_relu')(x)
#x = MaxPooling2D((3, 3), strides=(2, 2), name='pool1')(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')
for i in range(1, 8):
x = identity_block(x, 3, [128, 128, 512], stage=3, block='b' + str(i))
x = conv_block(x, 3, [256, 256, 1024], stage=4, block='a')
for i in range(1, 36):
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='b' + str(i))
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')
#####ADDED######
x = Conv2D(1024, (1, 1), name='conv99', use_bias=False)(x)
################
# if large_input:
# x = AveragePooling2D((14, 14), name='avg_pool')(x)
# else:
# x = AveragePooling2D((7, 7), name='avg_pool')(x)
# include classification layer by default, not included for feature extraction
# 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='resnet152')
# # load weights
# if weights == 'imagenet':
# if include_top:
# weights_path = get_file('resnet152_weights_tf.h5',
# WEIGHTS_PATH,
# cache_subdir='models',
# md5_hash='cdb18a2158b88e392c0905d47dcef965')
# else:
# weights_path = get_file('resnet152_weights_tf_notop.h5',
# WEIGHTS_PATH_NO_TOP,
# cache_subdir='models',
# md5_hash='4a90dcdafacbd17d772af1fb44fc2660')
# model.load_weights(weights_path, by_name=True)
# 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.')
return model
# if __name__ == '__main__':
# model = ResNet152(include_top=False, weights='imagenet')#(?,7,7,2048)
# img_path = './image.png'
# img = image.load_img(img_path, target_size=(224, 224))
# x = image.img_to_array(img)
# x = np.expand_dims(x, axis=0)
# print('Input image shape:', np.shape(x))
# preds = model.predict(x)
# print('Predicted:', np.shape(preds))
def ResNet152(include_top=True,
weights=None,
input_tensor=None,
input_shape=None,
large_input=False,
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')
eps = 1.1e-5
if large_input:
img_size = 448
else:
img_size = 224
# Determine proper input shape
input_shape = (224, 224, 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
# handle dimension ordering for different backends
if K.image_dim_ordering() == 'tf':
bn_axis = 3
else:
bn_axis = 1
x = ZeroPadding2D((3, 3), name='conv1_zeropadding')(img_input)
x = Conv2D(64, (7, 7), strides=(2, 2), name='conv1', use_bias=False)(x)
x = BatchNormalization(epsilon=eps, axis=bn_axis, name='bn_conv1')(x)
x = Scale(axis=bn_axis, name='scale_conv1')(x)
x = Activation('relu', name='conv1_relu')(x)
x = MaxPooling2D((3, 3), strides=(2, 2), name='pool1')(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')
for i in range(1, 8):
x = identity_block(x, 3, [128, 128, 512], stage=3, block='b' + str(i))
x = conv_block(x, 3, [256, 256, 1024], stage=4, block='a')
for i in range(1, 36):
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='b' + str(i))
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')
if large_input:
x = AveragePooling2D((14, 14), name='avg_pool')(x)
else:
x = AveragePooling2D((7, 7), name='avg_pool')(x)
# include classification layer by default, not included for feature extraction
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='resnet152')
# load weights
if weights == 'imagenet':
if include_top:
weights_path = get_file(
'resnet152_weights_tf.h5',
WEIGHTS_PATH,
cache_subdir='models',
md5_hash='cdb18a2158b88e392c0905d47dcef965')
else:
weights_path = get_file(
'resnet152_weights_tf_notop.h5',
WEIGHTS_PATH_NO_TOP,
cache_subdir='models',
md5_hash='4a90dcdafacbd17d772af1fb44fc2660')
model.load_weights(weights_path, by_name=True)
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.')
return model
def WideResidualNetwork(depth=28, width=8, dropout_rate=0.0,
include_top=True, weights='cifar10',
input_tensor=None, input_shape=None,
classes=10, activation='softmax'):
"""Instantiate the Wide Residual Network architecture,
optionally loading weights pre-trained
on CIFAR-10. 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
depth: number or layers in the DenseNet
width: multiplier to the ResNet width (number of filters)
dropout_rate: dropout rate
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).
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.
# 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 (depth - 4) % 6 != 0:
raise ValueError('Depth of the network must be such that (depth - 4)'
'should be divisible by 6.')
# Determine proper input shape
input_shape = _obtain_input_shape(input_shape,
default_size=32,
min_size=8,
data_format=K.image_dim_ordering(),
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_wide_residual_network(classes, img_input, include_top, depth, width,
dropout_rate, 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='wide-resnet')
# load weights
if weights == 'cifar10':
if (depth == 28) and (width == 8) and (dropout_rate == 0.0):
# Default parameters match. Weights for this model exist:
if K.image_dim_ordering() == 'th':
if include_top:
weights_path = get_file('wide_resnet_28_8_th_dim_ordering_th_kernels.h5',
TH_WEIGHTS_PATH,
cache_subdir='models')
else:
weights_path = get_file('wide_resnet_28_8_th_dim_ordering_th_kernels_no_top.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('wide_resnet_28_8_tf_dim_ordering_tf_kernels.h5',
TF_WEIGHTS_PATH,
cache_subdir='models')
else:
weights_path = get_file('wide_resnet_28_8_tf_dim_ordering_tf_kernels_no_top.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 create_model(input_tensor=None, input_shape=None, classes=7):
"""Creates C3D model with 3 more fully connected layers.
Args:
input_tensor: Tensor image to be processed
input_shape: String tuple (height, width, channels) of input image
classes: Integer number of classes
Returns:
Keras neural network model.
"""
K.set_image_data_format("channels_last")
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
# Layer 1
conv_1 = Convolution3D(64, (3, 3, 3),
strides=(1, 1, 1),
padding='same',
activation='relu',
name='conv_1',
data_format="channels_last")(img_input)
maxpool_1a = MaxPooling3D((2, 2, 2),
strides=(2, 2, 2),
name="maxpool_1a",
padding='same')(conv_1)
batchnorm_1 = BatchNormalization(name="batchnorm_1")(maxpool_1a)
# Layer 2
conv_2 = Convolution3D(128, (3, 3, 3),
strides=(1, 1, 1),
padding='same',
activation='relu',
name='conv_2',
data_format="channels_last")(batchnorm_1)
maxpool_2 = MaxPooling3D((2, 2, 2),
strides=(2, 2, 2),
name="maxpool_2",
padding='same')(conv_2)
# Layer 3
conv_3 = Convolution3D(256, (3, 3, 3),
strides=(1, 1, 1),
padding='same',
activation='relu',
name='conv_3',
data_format="channels_last")(maxpool_2)
# Layer 4
conv_4 = Convolution3D(256, (3, 3, 3),
strides=(1, 1, 1),
padding='same',
activation='relu',
name='conv_4',
data_format="channels_last")(conv_3)
maxpool_4 = MaxPooling3D((2, 2, 2),
strides=(2, 2, 2),
name="maxpool_4",
padding='same')(conv_4)
# Layer 5
conv_5 = Convolution3D(512, (3, 3, 3),
strides=(1, 1, 1),
padding='same',
activation='relu',
name='conv_5',
data_format="channels_last")(maxpool_4)
# Layer 6
conv_6 = Convolution3D(512, (3, 3, 3),
strides=(1, 1, 1),
padding='same',
activation='relu',
name='conv_6',
data_format="channels_last")(conv_5)
maxpool_6 = MaxPooling3D((2, 2, 2),
strides=(2, 2, 2),
name="maxpool_6",
padding='same')(conv_6)
# Layer 7
conv_7 = Convolution3D(512, (3, 3, 3),
strides=(1, 1, 1),
padding='same',
activation='relu',
name='conv_7',
data_format="channels_last")(maxpool_6)
# Layer 8
conv_8 = Convolution3D(512, (3, 3, 3),
strides=(1, 1, 1),
padding='same',
activation='relu',
name='conv_8',
data_format="channels_last")(conv_7)
maxpool_8 = MaxPooling3D((2, 2, 2),
strides=(2, 2, 2),
name="maxpool_8",
padding='same')(conv_8)
flat = Flatten(name='flatten')(maxpool_6)
fc_1 = Dense(4096, activation='relu', name='fc_1')(flat)
dropout_1 = Dropout(0.33, name='dropout_1')(fc_1)
net = Dense(classes, activation='softmax', name='predictions')(dropout_1)
# 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, net, name='MOC3D')
for layer in model.layers:
layer.trainable = True
return model
def SegNet(input_shape=(para.img_rows_seg, para.img_cols_seg, para.channels),
classes=para.seg_classes,
input_tensor=None,
alpha=1.0):
#img_input = Input(shape=input_shape)
img_input = Input(shape=input_shape)
# Encoder
x = Conv2D(64, (3, 3), padding="same")(img_input)
x = BatchNormalization()(x)
x = Activation("relu")(x)
x = SeparableConv2D(int(64 * alpha), (3, 3), padding="same")(x)
x = BatchNormalization()(x)
x = Activation("relu")(x)
x = MaxPooling2D(pool_size=(2, 2))(x)
x = SeparableConv2D(int(128 * alpha), (3, 3), padding="same")(x)
x = BatchNormalization()(x)
x = Activation("relu")(x)
x = SeparableConv2D(int(128 * alpha), (3, 3), padding="same")(x)
x = BatchNormalization()(x)
x = Activation("relu")(x)
x = MaxPooling2D(pool_size=(2, 2))(x)
x = SeparableConv2D(int(256 * alpha), (3, 3), padding="same")(x)
x = BatchNormalization()(x)
x = Activation("relu")(x)
x = SeparableConv2D(int(256 * alpha), (3, 3), padding="same")(x)
x = BatchNormalization()(x)
x = Activation("relu")(x)
x = SeparableConv2D(int(256 * alpha), (3, 3), padding="same")(x)
x = BatchNormalization()(x)
x = Activation("relu")(x)
x = MaxPooling2D(pool_size=(2, 2))(x)
x = SeparableConv2D(int(512 * alpha), (3, 3), padding="same")(x)
x = BatchNormalization()(x)
x = Activation("relu")(x)
x = SeparableConv2D(int(512 * alpha), (3, 3), padding="same")(x)
x = BatchNormalization()(x)
x = Activation("relu")(x)
x = SeparableConv2D(int(512 * alpha), (3, 3), padding="same")(x)
x = BatchNormalization()(x)
x = Activation("relu")(x)
encoder = Model(img_input, x, name='vgg16_encoder')
encoder_layers = [layer for _, layer in enumerate(encoder.layers)]
encoder_layers.reverse()
#for i, layer in enumerate(encoder_layers):
#print(i, layer)
# Decoder
x = SeparableConv2D(int(512 * alpha), (3, 3), padding="same")(x)
x = BatchNormalization()(x)
x = Activation("relu")(x)
x = SeparableConv2D(int(512 * alpha), (3, 3), padding="same")(x)
x = BatchNormalization()(x)
x = Activation("relu")(x)
x = SeparableConv2D(int(512 * alpha), (3, 3), padding="same")(x)
x = BatchNormalization()(x)
x = Activation("relu")(x)
x = DePool2D_Index(encoder_layers[9],
size=encoder_layers[9].pool_size,
input_shape=encoder.output_shape[1:])(x)
x = SeparableConv2D(encoder_layers[12].filters,
encoder_layers[12].kernel_size,
padding=encoder_layers[12].padding)(x)
x = BatchNormalization()(x)
x = Activation("relu")(x)
x = SeparableConv2D(encoder_layers[15].filters,
encoder_layers[15].kernel_size,
padding=encoder_layers[15].padding)(x)
x = BatchNormalization()(x)
x = Activation("relu")(x)
x = SeparableConv2D(encoder_layers[18].filters,
encoder_layers[18].kernel_size,
padding=encoder_layers[18].padding)(x)
x = BatchNormalization()(x)
x = Activation("relu")(x)
x = DePool2D_Index(encoder_layers[19],
size=encoder_layers[19].pool_size,
input_shape=encoder.output_shape[1:])(x)
x = SeparableConv2D(encoder_layers[22].filters,
encoder_layers[22].kernel_size,
padding=encoder_layers[22].padding)(x)
x = BatchNormalization()(x)
x = Activation("relu")(x)
x = SeparableConv2D(encoder_layers[25].filters,
encoder_layers[25].kernel_size,
padding=encoder_layers[25].padding)(x)
x = BatchNormalization()(x)
x = Activation("relu")(x)
x = DePool2D_Index(encoder_layers[26],
size=encoder_layers[26].pool_size,
input_shape=encoder.output_shape[1:])(x)
x = SeparableConv2D(encoder_layers[29].filters,
encoder_layers[29].kernel_size,
padding=encoder_layers[29].padding)(x)
x = BatchNormalization()(x)
x = Activation("relu")(x)
x = SeparableConv2D(encoder_layers[32].filters,
encoder_layers[32].kernel_size,
padding=encoder_layers[32].padding)(x)
x = BatchNormalization()(x)
x = Activation("relu")(x)
model = Model(img_input, x)
rows = model.output_shape[1]
cols = model.output_shape[2]
x = Conv2D(classes, (1, 1), padding="valid")(x)
x = Reshape(
(input_shape[0] * input_shape[1], classes))(x) # *****************
x = Activation("softmax")(x)
if input_tensor is not None:
inputs = get_source_inputs(input_tensor)
else:
inputs = img_input
model = Model(inputs, x)
return model, rows, cols
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,
attention_module=None):
"""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, attention_module)
# 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')
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 HRA_VGG19(include_top=True,
weights='HRA',
input_tensor=None,
input_shape=None,
mode='fine_tuning',
pooling_mode='avg',
classes=9,
data_augm_enabled=False):
"""Instantiates the VGG19 architecture fine-tuned (2 steps) on Human Rights Archive dataset.
Optionally loads weights pre-trained on Human Rights Archive Database.
# Arguments
include_top: whether to include the 3 fully-connected
layers at the top of the network.
weights: one of `None` (random initialization),
'HRA' (pre-training on Human Rights Archive),
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 input channels,
and width and height should be no smaller than 48.
E.g. `(200, 200, 3)` would be one valid value.
mode: one of `TL` (transfer learning - freeze all but the penultimate layer and re-train the last Dense layer)
or `FT` (fine-tuning - unfreeze the lower convolutional layers and retrain more layers) ,
pooling_mode: Pooling mode that will be applied to the output of the last convolutional layer of the original model
and thus the output of the model will be a 2D tensor.
- `avg` means that global average pooling_mode operation for spatial data will be applied.
- `max` means that global max pooling_mode operation for spatial data will be applied.
- `flatten` means that the output of the the last convolutional
layer of the original model will be flatten,
resulting in a larger Dense layer afterwards.
classes: optional number of classes to classify images into.
data_augm_enabled: whether to use the augmented samples during training.
# Returns
A Keras model instance.
# Raises
ValueError: in case of invalid argument for `weights`, or invalid input shape
"""
if not (weights in {'HRA', None} or os.path.exists(weights)):
raise ValueError('The `weights` argument should be either '
'`None` (random initialization), `HRA` '
'(pre-training on Human Rights Archive), '
'or the path to the weights file to be loaded.')
if not (mode in {'feature_extraction', 'fine_tuning'}):
raise ValueError(
'The `mode` argument should be either '
'`feature_extraction` (freeze all but the penultimate layer and re-train the last Dense layer),'
'or `fine_tuning` (unfreeze the lower convolutional layers and retrain more layers). '
)
if not (pooling_mode in {'avg', 'max', 'flatten'}):
raise ValueError(
'The `pooling_mode` argument should be either '
'`avg` (global average pooling_mode), `max` (global max pooling_mode)'
'or `flatten` (the output will be flatten). ')
if mode == 'feature_extraction' and include_top is False:
raise ValueError(
'The `include_top` argument can be set as false only '
'when the `mode` argument is `fine_tuning`. '
'If not, the returned model would have been literally the default '
'keras-applications model and not the one trained on HRA.')
cache_subdir = 'hra_models_fewer_params'
# 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,
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
# 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 the base pre-trained model
base_model = VGG19(weights='imagenet',
include_top=False,
input_tensor=img_input)
x = base_model.output
# Classification block - build a classifier model to put on top of the convolutional model
if include_top:
# add a global spatial pooling_mode layer or flatten the obtained output from the original model
if pooling_mode == 'avg':
x = GlobalAveragePooling2D(name='GAP')(x)
elif pooling_mode == 'max':
x = GlobalMaxPooling2D(name='GMP')(x)
elif pooling_mode == 'flatten':
x = Flatten(name='FLATTEN')(x)
# add a fully-connected layer
x = Dense(256, activation='relu', name='FC1')(x)
# When random init is enabled, we want to include Dropout,
# otherwise when loading a pre-trained HRA model we want to omit that layer,
# so the visualisations are done properly (there is an issue if it is included)
if weights is None:
x = Dropout(0.5, name='DROPOUT')(x)
# and a logistic layer with the number of classes defined by the `classes` argument
x = Dense(classes, activation='softmax', name='PREDICTIONS')(x)
model = Model(inputs=inputs, outputs=x, name='HRA-VGG19')
# load weights
if weights == 'HRA':
if include_top:
if mode == 'feature_extraction':
for layer in base_model.layers:
layer.trainable = False
model.compile(optimizer=SGD(lr=0.0001, momentum=0.9),
loss='categorical_crossentropy')
if data_augm_enabled:
if pooling_mode == 'avg':
weights_path = get_file(
AUGM_FEATURE_EXTRACTION_AVG_POOL_fname,
AUGM_FEATURE_EXTRACTION_AVG_POOL_WEIGHTS_PATH,
cache_subdir=cache_subdir)
elif pooling_mode == 'flatten':
weights_path = get_file(
AUGM_FEATURE_EXTRACTION_FLATTEN_POOL_fname,
AUGM_FEATURE_EXTRACTION_FLATTEN_POOL_WEIGHTS_PATH,
cache_subdir=cache_subdir)
elif pooling_mode == 'max':
weights_path = get_file(
AUGM_FEATURE_EXTRACTION_MAX_POOL_fname,
AUGM_FEATURE_EXTRACTION_MAX_POOL_WEIGHTS_PATH,
cache_subdir=cache_subdir)
else:
if pooling_mode == 'avg':
weights_path = get_file(
FEATURE_EXTRACTION_AVG_POOL_fname,
FEATURE_EXTRACTION_AVG_POOL_WEIGHTS_PATH,
cache_subdir=cache_subdir)
elif pooling_mode == 'flatten':
weights_path = get_file(
FEATURE_EXTRACTION_FLATTEN_POOL_fname,
FEATURE_EXTRACTION_FLATTEN_POOL_WEIGHTS_PATH,
cache_subdir=cache_subdir)
elif pooling_mode == 'max':
weights_path = get_file(
FEATURE_EXTRACTION_MAX_POOL_fname,
FEATURE_EXTRACTION_MAX_POOL_WEIGHTS_PATH,
cache_subdir=cache_subdir)
elif mode == 'fine_tuning':
if pooling_mode == 'flatten':
for layer in model.layers[:20]:
layer.trainable = False
for layer in model.layers[20:]:
layer.trainable = True
else:
for layer in model.layers[:19]:
layer.trainable = False
for layer in model.layers[19:]:
layer.trainable = True
model.compile(optimizer=SGD(lr=0.0001, momentum=0.9),
loss='categorical_crossentropy',
metrics=['accuracy'])
if data_augm_enabled:
if pooling_mode == 'avg':
weights_path = get_file(
AUGM_FINE_TUNING_AVG_POOL_fname,
AUGM_FINE_TUNING_AVG_POOL_WEIGHTS_PATH,
cache_subdir=cache_subdir)
elif pooling_mode == 'flatten':
weights_path = get_file(
AUGM_FINE_TUNING_FLATTEN_POOL_fname,
AUGM_FINE_TUNING_FLATTEN_POOL_WEIGHTS_PATH,
cache_subdir=cache_subdir)
elif pooling_mode == 'max':
weights_path = get_file(
AUGM_FINE_TUNING_MAX_POOL_fname,
AUGM_FINE_TUNING_MAX_POOL_WEIGHTS_PATH,
cache_subdir=cache_subdir)
else:
if pooling_mode == 'avg':
weights_path = get_file(
FINE_TUNING_AVG_POOL_fname,
FINE_TUNING_AVG_POOL_WEIGHTS_PATH,
cache_subdir=cache_subdir)
elif pooling_mode == 'flatten':
weights_path = get_file(
FINE_TUNING_FLATTEN_POOL_fname,
FINE_TUNING_FLATTEN_POOL_WEIGHTS_PATH,
cache_subdir=cache_subdir)
elif pooling_mode == 'max':
weights_path = get_file(
FINE_TUNING_MAX_POOL_fname,
FINE_TUNING_MAX_POOL_WEIGHTS_PATH,
cache_subdir=cache_subdir)
else:
weights_path = get_file(FINE_TUNING_WEIGHTS_PATH_NO_TOP_fname,
FINE_TUNING_WEIGHTS_PATH_NO_TOP,
cache_subdir=cache_subdir)
model.load_weights(weights_path)
elif weights is not None:
model.load_weights(weights)
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 MobileNetV2(input_shape=None,
alpha=1.0,
expansion_factor=6,
depth_multiplier=1,
dropout=1e-3,
include_top=True,
weights='imagenet',
input_tensor=None,
pooling=None,
classes=1000):
"""Instantiates the MobileNet architecture.
MobileNet V2 is from the paper:
- [Inverted Residuals and Linear Bottlenecks: Mobile Networks for Classification, Detection and Segmentation](https://arxiv.org/abs/1801.04381)
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.
expansion_factor: controls the expansion of the internal bottleneck
blocks. Should be a positive integer >= 1
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 and default size.
if input_shape is None:
default_size = 224
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 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 [0.35, 0.50, 0.75, 1.0, 1.3, 1.4]:
raise ValueError(
'If imagenet weights are being loaded, '
'alpha can be one of'
'`0.35`, `0.50`, `0.75`, `1.0`, `1.3` and `1.4` only.')
if rows != cols or rows not in [96, 128, 160, 192, 224]:
raise ValueError('If imagenet weights are being loaded, '
'input must have a static square shape (one of '
'(06, 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
x = _conv_block(img_input, 32, alpha, strides=(2, 2))
x = _depthwise_conv_block_v2(x, 16, alpha, 1, depth_multiplier, block_id=1)
x = _depthwise_conv_block_v2(x,
24,
alpha,
expansion_factor,
depth_multiplier,
block_id=2,
strides=(2, 2))
x = _depthwise_conv_block_v2(x,
24,
alpha,
expansion_factor,
depth_multiplier,
block_id=3)
x = _depthwise_conv_block_v2(x,
32,
alpha,
expansion_factor,
depth_multiplier,
block_id=4,
strides=(2, 2))
x = _depthwise_conv_block_v2(x,
32,
alpha,
expansion_factor,
depth_multiplier,
block_id=5)
x = _depthwise_conv_block_v2(x,
32,
alpha,
expansion_factor,
depth_multiplier,
block_id=6)
x = _depthwise_conv_block_v2(x,
64,
alpha,
expansion_factor,
depth_multiplier,
block_id=7,
strides=(2, 2))
x = _depthwise_conv_block_v2(x,
64,
alpha,
expansion_factor,
depth_multiplier,
block_id=8)
x = _depthwise_conv_block_v2(x,
64,
alpha,
expansion_factor,
depth_multiplier,
block_id=9)
x = _depthwise_conv_block_v2(x,
64,
alpha,
expansion_factor,
depth_multiplier,
block_id=10)
x = _depthwise_conv_block_v2(x,
96,
alpha,
expansion_factor,
depth_multiplier,
block_id=11)
x = _depthwise_conv_block_v2(x,
96,
alpha,
expansion_factor,
depth_multiplier,
block_id=12)
x = _depthwise_conv_block_v2(x,
96,
alpha,
expansion_factor,
depth_multiplier,
block_id=13)
x = _depthwise_conv_block_v2(x,
160,
alpha,
expansion_factor,
depth_multiplier,
block_id=14,
strides=(2, 2))
x = _depthwise_conv_block_v2(x,
160,
alpha,
expansion_factor,
depth_multiplier,
block_id=15)
x = _depthwise_conv_block_v2(x,
160,
alpha,
expansion_factor,
depth_multiplier,
block_id=16)
x = _depthwise_conv_block_v2(x,
320,
alpha,
expansion_factor,
depth_multiplier,
block_id=17)
if alpha <= 1.0:
penultimate_filters = 1280
else:
penultimate_filters = int(1280 * alpha)
x = _conv_block(x,
penultimate_filters,
alpha=1.0,
kernel=(1, 1),
block_id=18)
if include_top:
if K.image_data_format() == 'channels_first':
shape = (penultimate_filters, 1, 1)
else:
shape = (1, 1, penultimate_filters)
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 = Activation('sigmoid', name='act_sigmoid')(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='mobilenetV2_%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 == 1.3:
alpha_text = '1_3'
elif alpha == 1.4:
alpha_text = '1_4'
elif alpha == 0.75:
alpha_text = '7_5'
elif alpha == 0.50:
alpha_text = '5_0'
else:
alpha_text = '3_5'
if include_top:
model_name = 'mobilenet_v2_%s_%d_tf.h5' % (alpha_text, rows)
weigh_path = BASE_WEIGHT_PATH_V2 + model_name
weights_path = get_file(model_name,
weigh_path,
cache_subdir='models')
else:
model_name = 'mobilenet_v2_%s_%d_tf_no_top.h5' % (alpha_text, rows)
weigh_path = BASE_WEIGHT_PATH_V2 + 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 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 InceptionV3(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)
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.
"""
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
x = conv2d_bn(img_input, 32, 3, 3, strides=(2, 2), padding='valid')
x = conv2d_bn(x, 32, 3, 3, padding='valid')
x = conv2d_bn(x, 64, 3, 3)
x = MaxPooling2D((3, 3), strides=(2, 2))(x)
x = conv2d_bn(x, 80, 1, 1, padding='valid')
x = conv2d_bn(x, 192, 3, 3, padding='valid')
x = MaxPooling2D((3, 3), strides=(2, 2))(x)
# mixed 0, 1, 2: 35 x 35 x 256
for i in range(3):
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='mixed' + str(i))
# mixed 3: 17 x 17 x 768
branch3x3 = conv2d_bn(x, 384, 3, 3, strides=(2, 2), padding='valid')
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='valid')
branch_pool = MaxPooling2D((3, 3), strides=(2, 2))(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, 160, 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='valid')
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='valid')
branch_pool = AveragePooling2D((3, 3), strides=(2, 2))(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',
md5_hash='fe114b3ff2ea4bf891e9353d1bbfb32f')
else:
weights_path = get_file('inception_v3_weights_tf_dim_ordering_tf_kernels_notop.h5',
WEIGHTS_PATH_NO_TOP,
cache_subdir='models',
md5_hash='2f3609166de1d967d1a481094754f691')
model.load_weights(weights_path)
if K.backend() == 'theano':
convert_all_kernels_in_model(model)
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 Xception(include_top=True, weights=None,
input_tensor=None, input_shape=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 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='require_flatten')
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 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 DenseNet(input_shape=None,
depth=40,
nb_dense_block=3,
growth_rate=12,
nb_filter=16,
nb_layers_per_block=-1,
bottleneck=False,
reduction=0.0,
dropout_rate=0.0,
weight_decay=1E-4,
include_top=False,
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 factor
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.
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.
'''
# Determine proper input shape
input_shape = _obtain_input_shape(input_shape,
default_size=32,
min_size=8,
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 = __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, 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')
if K.backend() == 'theano':
convert_all_kernels_in_model(model)
return model
def SqueezeNet(include_top=True,
weights='imagenet',
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000):
"""Instantiates the SqueezeNet architecture.
"""
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(),
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 = 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)
if include_top:
# It's not obvious where to cut the network...
# Could do the 8th or 9th layer... some work recommends cutting earlier layers.
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)
x = Activation('softmax', name='loss')(x)
else:
if pooling == 'avg':
x = GlobalAveragePooling2D()(x)
elif pooling == 'max':
x = GlobalMaxPooling2D()(x)
elif pooling == None:
pass
else:
raise ValueError("Unknown argument for 'pooling'=" + 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
model = Model(inputs, x, name='squeezenet')
# load weights
if weights == 'imagenet':
if include_top:
weights_path = get_file(
'squeezenet_weights_tf_dim_ordering_tf_kernels.h5',
WEIGHTS_PATH,
cache_subdir='models')
else:
weights_path = get_file(
'squeezenet_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 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 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_dim_ordering(),
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 = AveragePooling2D((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 = AveragePooling2D((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 = AveragePooling2D((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 = AveragePooling2D((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 = 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 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
bn_eps = 0.0001
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',epsilon=bn_eps)(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 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)
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.
"""
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)
x = Lambda(lambda t: t, name='before_last_conv_passthrough')(x)
# 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')
model = load_weights(model, weights=weights, include_top=include_top)
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,
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
# 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 = AveragePooling2D((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 = AveragePooling2D((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 = AveragePooling2D((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 = AveragePooling2D((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 = 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)
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 NASNet(input_shape=None,
penultimate_filters=4032,
nb_blocks=6,
stem_filters=96,
skip_reduction=True,
use_auxiliary_branch=False,
filters_multiplier=2,
dropout=0.5,
weight_decay=5e-5,
include_top=True,
weights=None,
input_tensor=None,
pooling=None,
classes=1000,
default_size=None):
"""Instantiates a NASNet 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`.
# Arguments
input_shape: optional shape tuple, only to be specified
if `include_top` is False (otherwise the input shape
has to be `(331, 331, 3)` for NASNetLarge or
`(224, 224, 3)` for NASNetMobile
It should have exactly 3 inputs channels,
and width and height should be no smaller than 32.
E.g. `(224, 224, 3)` would be one valid value.
penultimate_filters: number of filters in the penultimate layer.
NASNet models use the notation `NASNet (N @ P)`, where:
- N is the number of blocks
- P is the number of penultimate filters
nb_blocks: number of repeated blocks of the NASNet model.
NASNet models use the notation `NASNet (N @ P)`, where:
- N is the number of blocks
- P is the number of penultimate filters
stem_filters: number of filters in the initial stem block
skip_reduction: Whether to skip the reduction step at the tail
end of the network. Set to `False` for CIFAR models.
use_auxiliary_branch: Whether to use the auxiliary branch during
training or evaluation.
filters_multiplier: controls the width of the network.
- If `filters_multiplier` < 1.0, proportionally decreases the number
of filters in each layer.
- If `filters_multiplier` > 1.0, proportionally increases the number
of filters in each layer.
- If `filters_multiplier` = 1, default number of filters from the paper
are used at each layer.
dropout: dropout rate
weight_decay: l2 regularization weight
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.
default_size: specifies the default image size of the model
# 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 '
'separable convolution.')
if weights not in {'imagenet', None} and not os.path.exists(weights):
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 default_size is None:
default_size = 331
# Determine proper input shape and default size.
input_shape = _obtain_input_shape(input_shape,
default_size=default_size,
min_size=32,
data_format=K.image_data_format(),
require_flatten=include_top or weights)
if K.image_data_format() != 'channels_last':
warnings.warn('The NASNet 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
assert penultimate_filters % 24 == 0, "`penultimate_filters` needs to be divisible " \
"by 24."
channel_dim = 1 if K.image_data_format() == 'channels_first' else -1
filters = penultimate_filters // 24
if not skip_reduction:
x = Conv2D(stem_filters, (3, 3),
strides=(2, 2),
padding='valid',
use_bias=False,
name='stem_conv1',
kernel_initializer='he_normal',
kernel_regularizer=l2(weight_decay))(img_input)
else:
x = Conv2D(stem_filters, (3, 3),
strides=(1, 1),
padding='same',
use_bias=False,
name='stem_conv1',
kernel_initializer='he_normal',
kernel_regularizer=l2(weight_decay))(img_input)
x = BatchNormalization(axis=channel_dim,
momentum=_BN_DECAY,
epsilon=_BN_EPSILON,
name='stem_bn1')(x)
p = None
if not skip_reduction: # imagenet / mobile mode
x, p = _reduction_A(x,
p,
filters // (filters_multiplier**2),
weight_decay,
id='stem_1')
x, p = _reduction_A(x,
p,
filters // filters_multiplier,
weight_decay,
id='stem_2')
for i in range(nb_blocks):
x, p = _normal_A(x, p, filters, weight_decay, id='%d' % (i))
x, p0 = _reduction_A(x,
p,
filters * filters_multiplier,
weight_decay,
id='reduce_%d' % (nb_blocks))
p = p0 if not skip_reduction else p
for i in range(nb_blocks):
x, p = _normal_A(x,
p,
filters * filters_multiplier,
weight_decay,
id='%d' % (nb_blocks + i + 1))
auxiliary_x = None
if not skip_reduction: # imagenet / mobile mode
if use_auxiliary_branch:
auxiliary_x = _add_auxiliary_head(x, classes, weight_decay)
x, p0 = _reduction_A(x,
p,
filters * filters_multiplier**2,
weight_decay,
id='reduce_%d' % (2 * nb_blocks))
if skip_reduction: # CIFAR mode
if use_auxiliary_branch:
auxiliary_x = _add_auxiliary_head(x, classes, weight_decay)
p = p0 if not skip_reduction else p
for i in range(nb_blocks):
x, p = _normal_A(x,
p,
filters * filters_multiplier**2,
weight_decay,
id='%d' % (2 * nb_blocks + i + 1))
x = Activation('relu')(x)
if include_top:
x = GlobalAveragePooling2D()(x)
x = Dropout(dropout)(x)
x = Dense(classes,
activation='softmax',
kernel_regularizer=l2(weight_decay),
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.
if use_auxiliary_branch:
model = Model(inputs, [x, auxiliary_x], name='NASNet_with_auxiliary')
else:
model = Model(inputs, x, name='NASNet')
# load weights
if weights == 'imagenet':
if default_size == 224: # mobile version
if include_top:
if use_auxiliary_branch:
weight_path = NASNET_MOBILE_WEIGHT_PATH_WITH_AUXULARY
model_name = 'nasnet_mobile_with_aux.h5'
else:
weight_path = NASNET_MOBILE_WEIGHT_PATH
model_name = 'nasnet_mobile.h5'
else:
if use_auxiliary_branch:
weight_path = NASNET_MOBILE_WEIGHT_PATH_WITH_AUXULARY_NO_TOP
model_name = 'nasnet_mobile_with_aux_no_top.h5'
else:
weight_path = NASNET_MOBILE_WEIGHT_PATH_NO_TOP
model_name = 'nasnet_mobile_no_top.h5'
weights_file = get_file(model_name,
weight_path,
cache_subdir='models')
model.load_weights(weights_file, by_name=True)
elif default_size == 331: # large version
if include_top:
if use_auxiliary_branch:
weight_path = NASNET_LARGE_WEIGHT_PATH_WITH_auxiliary
model_name = 'nasnet_large_with_aux.h5'
else:
weight_path = NASNET_LARGE_WEIGHT_PATH
model_name = 'nasnet_large.h5'
else:
if use_auxiliary_branch:
weight_path = NASNET_LARGE_WEIGHT_PATH_WITH_auxiliary_NO_TOP
model_name = 'nasnet_large_with_aux_no_top.h5'
else:
weight_path = NASNET_LARGE_WEIGHT_PATH_NO_TOP
model_name = 'nasnet_large_no_top.h5'
weights_file = get_file(model_name,
weight_path,
cache_subdir='models')
model.load_weights(weights_file, by_name=True)
else:
raise ValueError(
'ImageNet weights can only be loaded on NASNetLarge or NASNetMobile'
)
elif weights is not None:
model.load_weights(weights, by_name=True)
if old_data_format:
K.set_image_data_format(old_data_format)
return model
def ResNextImageNet(input_shape=None,
depth=[3, 4, 6, 3],
cardinality=32,
width=4,
weight_decay=5e-4,
include_top=True,
weights=None,
input_tensor=None,
pooling=None,
classes=1000):
""" Instantiate the ResNeXt architecture for the ImageNet dataset. 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 each block, defined as a list.
ResNeXt-50 can be defined as [3, 4, 6, 3].
ResNeXt-101 can be defined as [3, 4, 23, 3].
Defaults is ResNeXt-50.
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) or `imagenet` (trained
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 `tf` dim ordering)
or `(3, 224, 224)` (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 {'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 type(depth) == int and (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=224,
min_size=112,
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_imagenet(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 == 'imagenet':
if (depth == [3, 4, 6, 3]) and (cardinality == 32) and (width == 4):
# Default parameters match. Weights for this model exist:
if K.image_data_format() == 'channels_first':
if include_top:
weights_path = get_file(
'resnext_imagenet_32_4_th_dim_ordering_th_kernels.h5',
IMAGENET_TH_WEIGHTS_PATH,
cache_subdir='models')
else:
weights_path = get_file(
'resnext_imagenet_32_4_th_dim_ordering_th_kernels_no_top.h5',
IMAGENET_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_imagenet_32_4_tf_dim_ordering_tf_kernels.h5',
IMAGENET_TF_WEIGHTS_PATH,
cache_subdir='models')
else:
weights_path = get_file(
'resnext_imagenet_32_4_tf_dim_ordering_tf_kernels_no_top.h5',
IMAGENET_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(include_top=True,
weights='imagenet',
input_tensor=None,
input_shape=None,
classes=1000):
"""Instantiate the VGG16 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.
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 `tf` dim ordering)
or `(3, 224, 244)` (with `th` dim ordering).
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.
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 {'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, # Changed from original source to allow cifar10 data
data_format=K.image_dim_ordering(),
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',
border_mode='same',
name='block1_conv1')(img_input)
x = Conv2D(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 = Conv2D(128,
3,
3,
activation='relu',
border_mode='same',
name='block2_conv1')(x)
x = Conv2D(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 = Conv2D(256,
3,
3,
activation='relu',
border_mode='same',
name='block3_conv1')(x)
x = Conv2D(256,
3,
3,
activation='relu',
border_mode='same',
name='block3_conv2')(x)
x = Conv2D(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 = Conv2D(512,
3,
3,
activation='relu',
border_mode='same',
name='block4_conv1')(x)
x = Conv2D(512,
3,
3,
activation='relu',
border_mode='same',
name='block4_conv2')(x)
x = Conv2D(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 = Conv2D(512,
3,
3,
activation='relu',
border_mode='same',
name='block5_conv1')(x)
x = Conv2D(512,
3,
3,
activation='relu',
border_mode='same',
name='block5_conv2')(x)
x = Conv2D(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 = 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 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='deconv'):
'''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
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 'upsampling', 'deconv' 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', '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)
# 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 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 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')
# load weights
if weights == 'imagenet':
weights_loaded = False
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 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 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 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 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 ShuffleNetV2(include_top=True,
input_tensor=None,
scale_factor=1.0,
pooling='max',
input_shape=(224, 224, 3),
weights_path=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]))
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 = {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 = MaxPool2D(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 weights_path:
model.load_weights(weights_path, by_name=True)
return model
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 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 InceptionV3(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)
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.
"""
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:
img_input = Input(tensor=input_tensor, shape=input_shape)
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='valid')
x = conv2d_bn(x, 32, 3, 3, padding='valid')
x = conv2d_bn(x, 64, 3, 3)
x = MaxPooling2D((3, 3), strides=(2, 2))(x)
x = conv2d_bn(x, 80, 1, 1, padding='valid')
x = conv2d_bn(x, 192, 3, 3, padding='valid')
x = MaxPooling2D((3, 3), strides=(2, 2))(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='valid')
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='valid')
branch_pool = MaxPooling2D((3, 3), strides=(2, 2))(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='valid')
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='valid')
branch_pool = MaxPooling2D((3, 3), strides=(2, 2))(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',
md5_hash='9a0d58056eeedaa3f26cb7ebd46da564')
else:
weights_path = get_file(
'inception_v3_weights_tf_dim_ordering_tf_kernels_notop.h5',
WEIGHTS_PATH_NO_TOP,
cache_subdir='models',
md5_hash='bcbd6486424b2319ff4ef7d526e38f63')
model.load_weights(weights_path)
if K.backend() == 'theano':
convert_all_kernels_in_model(model)
return model
def fcn_8(input_shape=(para.img_cols, para.img_rows, para.channels),
classes=para.num_classes,
input_tensor=None):
#img_input = Input(shape=input_shape)
input_shape = _obtain_input_shape(input_shape,
default_size=224,
min_size=56,
data_format=K.image_data_format(),
include_top=False)
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
#print(img_input.shape)
x = img_input
# Encoder
x = Conv2D(64, (3, 3), padding="same", name="block1_conv0")(x)
x = BatchNormalization()(x)
x = Activation("relu")(x)
x = Conv2D(64, (3, 3), padding="same", name="block1_conv1")(x)
x = BatchNormalization()(x)
x = Activation("relu")(x)
x = MaxPooling2D(pool_size=(2, 2))(x)
y1 = x
x = Conv2D(128, (3, 3), padding="same", name="block2_conv0")(x)
x = BatchNormalization()(x)
x = Activation("relu")(x)
x = Conv2D(128, (3, 3), padding="same", name="block2_conv1")(x)
x = BatchNormalization()(x)
x = Activation("relu")(x)
x = MaxPooling2D(pool_size=(2, 2))(x)
y2 = x
x = Conv2D(256, (3, 3), padding="same", name="block3_conv0")(x)
x = BatchNormalization()(x)
x = Activation("relu")(x)
x = Conv2D(256, (3, 3), padding="same", name="block3_conv1")(x)
x = BatchNormalization()(x)
x = Activation("relu")(x)
x = Conv2D(256, (3, 3), padding="same", name="block3_conv2")(x)
x = BatchNormalization()(x)
x = Activation("relu")(x)
x = MaxPooling2D(pool_size=(2, 2))(x)
y3 = x
x = Conv2D(512, (3, 3), padding="same", name="block4_conv0")(x)
x = BatchNormalization()(x)
x = Activation("relu")(x)
x = Conv2D(512, (3, 3), padding="same", name="block4_conv1")(x)
x = BatchNormalization()(x)
x = Activation("relu")(x)
x = Conv2D(512, (3, 3), padding="same", name="block4_conv2")(x)
x = BatchNormalization()(x)
x = Activation("relu")(x)
x = MaxPooling2D(pool_size=(2, 2))(x)
y4 = x
x = Conv2D(512, (3, 3), padding="same", name="block5_conv0")(x)
x = BatchNormalization()(x)
x = Activation("relu")(x)
x = Conv2D(512, (3, 3), padding="same", name="block5_conv1")(x)
x = BatchNormalization()(x)
x = Activation("relu")(x)
x = Conv2D(512, (3, 3), padding="same", name="block5_conv2")(x)
x = BatchNormalization()(x)
x = Activation("relu")(x)
y5 = x
# =============
# The Decoder
# =============
# Block 6
o = y5
o = (Conv2D(classes, (1, 1), padding='same', name='block6_conv1'))(o)
# Block 7
o2 = y4
o2 = (Conv2D(classes, (1, 1), padding='same', name='block7_conv1'))(o2)
o, o2 = crop(o, o2, img_input)
o = Add()([o, o2])
o = UpSampling2D(size=(2, 2))(o)
# Block 8
o2 = y3
o2 = (Conv2D(classes, (1, 1), padding='same', name='block8_conv1'))(o2)
o2, o = crop(o2, o, img_input)
o = Add()([o2, o])
o = UpSampling2D(size=(2, 2))(o)
# Block 9
o2 = y2
o2 = (Conv2D(classes, (1, 1), padding='same', name='block9_conv1'))(o2)
o2, o = crop(o2, o, img_input)
o = Add()([o2, o])
o = UpSampling2D(size=(2, 2))(o)
# Block 10
o2 = y1
o2 = (Conv2D(classes, (1, 1), padding='same', name='block10_conv1'))(o2)
o2, o = crop(o2, o, img_input)
o = Add()([o2, o])
o = UpSampling2D(size=(2, 2))(o)
model = Model(img_input, o)
cols = model.output_shape[1]
rows = model.output_shape[2]
o = Conv2D(classes, (1, 1), padding="valid")(o)
o = Reshape((cols * rows, classes))(o) # *****************
o = Activation("softmax")(o)
if input_tensor is not None:
inputs = get_source_inputs(input_tensor)
else:
inputs = img_input
model = Model(inputs, o)
return model, rows, cols
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 SEResNet(input_shape=None,
initial_conv_filters=64,
depth=[3, 4, 6, 3],
filters=[64, 128, 256, 512],
width=1,
bottleneck=False,
weight_decay=1e-4,
include_top=True,
weights=None,
input_tensor=None,
pooling=None,
classes=1000):
""" Instantiate the Squeeze and Excite ResNet 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
initial_conv_filters: number of features for the initial convolution
depth: number or layers in the each block, defined as a list.
ResNet-50 = [3, 4, 6, 3]
ResNet-101 = [3, 6, 23, 3]
ResNet-152 = [3, 8, 36, 3]
filter: number of filters per block, defined as a list.
filters = [64, 128, 256, 512
width: width multiplier for the network (for Wide ResNets)
bottleneck: adds a bottleneck conv to reduce computation
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) or `imagenet` (trained
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 `tf` dim ordering)
or `(3, 224, 224)` (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 {'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')
assert len(depth) == len(filters), "The length of filter increment list must match the length " \
"of the depth list."
# Determine proper input shape
input_shape = _obtain_input_shape(input_shape,
default_size=224,
min_size=32,
data_format=K.image_data_format(),
require_flatten=False)
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_se_resnet(classes, img_input, include_top,
initial_conv_filters, filters, depth, width,
bottleneck, 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=inputs, outputs=x, name='resnext')
# load weights
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 create_model(classes=10, input_shape=None, config=None,
depth=28, width=8, dropout_rate=0.0,
include_top=True, weights=None,
input_tensor=None):
"""
Create wide resnet.
Instantiate the Wide Residual Network architecture, optionally loading
weights pre-trained on CIFAR-10. 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.
Parameters
----------
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.
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.
depth: number or layers in the DenseNet
width: multiplier to the ResNet width (number of filters)
dropout_rate: dropout rate
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.
# 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 (depth - 4) % 6 != 0:
raise ValueError('Depth of the network must be such that (depth - 4)'
'should be divisible by 6.')
# Determine proper input shape
input_shape = _obtain_input_shape(input_shape,
default_size=32,
min_size=8,
data_format=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
x = __create_wide_residual_network(classes, img_input, include_top, depth,
width, dropout_rate)
# 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='wide-resnet')
# load weights
if weights == 'cifar10':
if (depth == 28) and (width == 8) and (dropout_rate == 0.0):
# Default parameters match. Weights for this model exist:
if K.image_dim_ordering() == 'th':
if include_top:
weights_path = get_file(('wide_resnet_28_8_th_dim_ordering'
'_th_kernels.h5'),
TH_WEIGHTS_PATH,
cache_subdir='models')
else:
weights_path = get_file(('wide_resnet_28_8_th_dim_ordering'
'_th_kernels_no_top.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 '
' youare 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(('wide_resnet_28_8_tf_dim_ordering'
'_tf_kernels.h5'),
TF_WEIGHTS_PATH,
cache_subdir='models')
else:
weights_path = get_file(('wide_resnet_28_8_tf_dim_ordering'
'_tf_kernels_no_top.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
