def cnn_lstm_model():
''' '''
print('Build model...')
inputs = Input(shape=(maxlen, ), dtype='int32')
x = Embedding(max_features, embedding_size, input_length=maxlen)(inputs)
x = Dropout(0.25)(x)
x = Conv1D(filters,
kernel_size,
padding='valid',
activation='relu',
strides=1)(x)
x = MaxPooling1D(pool_size=pool_size)(x)
x = LSTM(lstm_output_size)(x)
x = Dense(1, activation='sigmoid')(x)
model = Model(inputs=inputs, outputs=x)
model.compile(loss='binary_crossentropy',
optimizer='adam',
metrics=['accuracy'])
return model
def build_model(num_output_classes):
conv1size = 32
conv2size = 64
convfiltsize = 4
densesize = 128
poolsize = (2, 2)
imgdepth = 3
dropout = 0.3
if IMG_COLORMODE == 'grayscale':
imgdepth = 1
inpshape = IMG_TGT_SIZE + (imgdepth, )
inputs = Input(shape=inpshape)
conv1 = Convolution2D(conv1size,
convfiltsize,
strides=(1, 1),
padding='valid',
activation='relu',
name='conv1',
data_format='channels_last')(inputs)
pool1 = MaxPooling2D(pool_size=poolsize, name='pool1')(conv1)
drop1 = Dropout(dropout)(pool1)
conv2 = Convolution2D(conv2size,
convfiltsize,
strides=(1, 1),
padding='valid',
activation='relu',
name='conv2',
data_format='channels_last')(drop1)
pool2 = MaxPooling2D(pool_size=poolsize, name='pool2')(conv2)
drop2 = Dropout(dropout)(pool2)
flat2 = Flatten()(drop2)
dense = Dense(densesize, name='dense')(flat2)
denseact = Activation('relu')(dense)
output = Dense(num_output_classes, name='output')(denseact)
outputact = Activation('softmax')(output)
model = Model(inputs=inputs, outputs=outputact)
model.compile(loss='categorical_crossentropy',
optimizer='adam',
metrics=['accuracy'])
return model
def cnn_model_fn():
'''
define the model in function way
'''
# input shape is (img_rows, img_cols, fea_channel)
inputs = Input(shape=(img_rows, img_cols, 1))
x = Conv2D(32, kernel_size=(3, 3), activation='relu')(inputs)
x = Conv2D(64, (3, 3), activation='relu')(x)
x = MaxPooling2D(pool_size=(2, 2))(x)
x = Dropout(0.25)(x)
x = Flatten()(x)
x = Dense(128, activation='relu')(x)
x = Dropout(0.5)(x)
pred = Dense(num_classes, activation='softmax')(x)
# small change of Model parameters names, now is inputs, outputs
model = Model(inputs=inputs, outputs=pred)
model.compile(loss='categorical_crossentropy',
optimizer='adadelta',
metrics=['accuracy'])
return model
def cnn_model_fn():
''' '''
print('Build model...')
inputs = Input(shape=(maxlen, ),
dtype='int32') # a index sequence with lenght = maxlen
x = Embedding(max_features, embedding_dims, input_length=maxlen)(inputs)
x = Dropout(0.2)(x)
x = Conv1D(filters,
kernel_size,
padding='valid',
activation='relu',
strides=1)(x)
x = GlobalMaxPooling1D()(x)
x = Dense(hidden_dims)(x)
x = Dropout(0.2)(x)
x = Activation('relu')(x)
x = Dense(1)(x)
x = Activation('sigmoid')(x)
model = Model(inputs=inputs, outputs=x)
model.compile(loss='binary_crossentropy',
optimizer='adam',
metrics=['accuracy'])
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 input 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':
logging.warning(
'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(),
require_flatten=False,
weights=weights)
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
img_input = Input(tensor=input_tensor, shape=input_shape)
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 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, 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.
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:
img_input = Input(tensor=input_tensor, shape=input_shape)
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')
x0 = x
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')
# 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, x0], 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 = "./saved_model/resnet50_weights_tf_dim_ordering_tf_kernels_notop.h5"
model.load_weights(weights_path)
return model
y = X[:, 0] ^ X[:, 1] # ^ is xor function
#######################################################
# Sequential can specify more activations layer from normal layers than Model
#######################################################
# check whether 3 models are the same or not
model = Sequential()
model.add(Dense(4, input_dim=2,
name='dense1')) # 2 nodes reaches 50% accuracy, 8 nodes 100%
model.add(Activation('relu', name='dense1_act'))
model.add(Dense(1, name='dense2'))
model.add(Activation('sigmoid', name='dense2_act')) # output shaped by sigmoid
model.summary() # see each layer of a model
# use Model instead of Sequential
input_tensor = Input(shape=(2, ), name='input')
hidden = Dense(4, activation='relu', name='dense1_relu')(input_tensor)
output = Dense(1, activation='sigmoid',
name='dense2_sigm')(hidden) # output shaped by sigmoid
model1 = Model(inputs=input_tensor, outputs=output)
model1.summary() # see each layer of a model
"""
# use Model to split layer and activation
input_tensor = Input(shape=(2,))
hidden = Dense(2)(input_tensor)
relu_hid = K.relu(hidden)
dense_out = Dense(1)(relu_hid) # output shaped by sigmoid
sigmoid_out = K.sigmoid(dense_out)
# inputs and outputs must be layer tensor, not just tensor made from K
model2 = Model(inputs=input_tensor, outputs=sigmoid_out)
""" ### Shared vision model This model re-uses the same image-processing module on two inputs, to classify whether two MNIST digits are the same digit or different digits. """ from tensorflow.contrib.keras.python.keras.layers import Conv2D, MaxPooling2D, Input, Dense, Flatten, concatenate from tensorflow.contrib.keras.python.keras.models import Model # First, define the vision modules # digit_input = Input(shape=(1, 27, 27)) digit_input = Input(shape=(27, 27, 1)) x = Conv2D(64, (3, 3))(digit_input) # padding 'valid' or 'same' affect shape x = Conv2D(64, (3, 3))(x) # padding='same', can keep image size the same x = MaxPooling2D((2, 2))(x) # downscale image size out = Flatten()(x) vision_model = Model(digit_input, out) # Then define the tell-digits-apart model # digit_a = Input(shape=(1, 27, 27)) # digit_b = Input(shape=(1, 27, 27)) digit_a = Input(shape=(27, 27, 1)) digit_b = Input(shape=(27, 27, 1)) # The vision model will be shared, weights and all out_a = vision_model(digit_a) out_b = vision_model(digit_b) concatenated = concatenate([out_a, out_b]) # cbind tensors
def create_model(input_shape, k=1, lr=0.001):
inputs = Input(shape=input_shape)
i = 0
nb_filter = [16, 32, 64, 128, 256, 512, 256, 128, 64, 32, 16]
#0
x = Conv2D(nb_filter[i] * k, (3, 3), padding='same',
use_bias=False)(inputs)
x = BN(x)
x = Activation('relu')(x)
x = Conv2D(nb_filter[i] * k, (3, 3), padding='same', use_bias=False)(x)
x0 = BN(x)
x = Activation('relu')(x0)
i += 1
#1
x = dw_conv(x0, nb_filter[i], k)
x = res_block(x, k, nb_filter[i])
x1 = res_block(x, k, nb_filter[i])
i += 1
#2
x = dw_conv(x1, nb_filter[i], k)
x = res_block(x, k, nb_filter[i])
x2 = res_block(x, k, nb_filter[i])
i += 1
#3
x = dw_conv(x2, nb_filter[i], k)
x = res_block(x, k, nb_filter[i])
x3 = res_block(x, k, nb_filter[i])
i += 1
#4
x = dw_conv(x3, nb_filter[i], k)
x = res_block(x, k, nb_filter[i])
x4 = res_block(x, k, nb_filter[i])
i += 1
#--------------- center ------------
x = dw_conv(x4, nb_filter[i], k)
x = res_block(x, k, nb_filter[i])
x = res_block(x, k, nb_filter[i])
#--------------- center ------------
i += 1
#4
x = up_conv(x, x4, nb_filter[i], k)
x = res_block(x, k, nb_filter[i])
x = res_block(x, k, nb_filter[i])
i += 1
#3
x = up_conv(x, x3, nb_filter[i], k)
x = res_block(x, k, nb_filter[i])
x = res_block(x, k, nb_filter[i])
i += 1
#2
x = up_conv(x, x2, nb_filter[i], k)
x = res_block(x, k, nb_filter[i])
x = res_block(x, k, nb_filter[i])
i += 1
#1
x = up_conv(x, x1, nb_filter[i], k)
x = res_block(x, k, nb_filter[i])
x = res_block(x, k, nb_filter[i])
i += 1
#0
x = up_conv(x, x0, nb_filter[i], k)
x = res_block(x, k, nb_filter[i])
x = res_block(x, k, nb_filter[i])
x = Activation('relu')(x)
classify = Conv2D(1, (1, 1), activation='sigmoid')(x)
model = Model(inputs=inputs, outputs=classify)
model.compile(optimizer=RMSprop(lr=lr),
loss=bce_dice_loss,
metrics=[dice_loss])
return model
embedding_matrix = np.zeros((len(word_index) + 1, EMBEDDING_DIM))
for word, i in word_index.items():
embedding_vector = embeddings_index.get(word)
if embedding_vector is not None:
# words not found in embedding index will be all-zeros.
embedding_matrix[i] = embedding_vector
embedding_layer = Embedding(len(word_index) + 1,
EMBEDDING_DIM,
weights=[embedding_matrix],
input_length=MAX_SEQUENCE_LENGTH,
trainable=False)
# Training
sequence_input = Input(shape=(MAX_SEQUENCE_LENGTH, ), dtype='int32')
embedded_sequences = embedding_layer(sequence_input)
x = Conv1D(128, 5, activation='relu')(embedded_sequences)
print('sequence_input: ', sequence_input)
print('embedded_sequences: ', embedded_sequences)
print('x: ', x)
x = MaxPooling1D(5)(x)
x = Conv1D(128, 5, activation='relu')(x)
x = MaxPooling1D(5)(x)
x = Conv1D(128, 5, activation='relu')(x)
x = MaxPooling1D(35)(x) # global max pooling
x = Flatten()(x)
x = Dense(128, activation='relu')(x)
def make_trainable(net, val):
net.trainable = val
for l in net.layers:
l.trainable = val
shp = X_train.shape[1:]
dropout_rate = 0.25
opt = Adam(lr=1e-4)
dopt = Adam(lr=1e-3)
# Build Generative model ...
nch = 200
g_input = Input(shape=[100])
H = Dense(nch * 14 * 14,
kernel_initializer=init_ops.glorot_normal_initializer())(g_input)
H = BatchNormalization()(H)
H = Activation('relu')(H)
H = Reshape([14, 14, nch])(H)
H = UpSampling2D(size=(2, 2))(H)
H = Conv2D(nch / 2,
kernel_size=(3, 3),
padding='same',
kernel_initializer=init_ops.glorot_normal_initializer(),
name='Convolution_1')(H)
H = BatchNormalization()(H)
H = Activation('relu')(H)
H = Conv2D(nch / 4,
kernel_size=(3, 3),
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 = WEIGHTS_PATH
else:
weights_path = WEIGHTS_PATH_NO_TOP
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
To "freeze" a layer means to exclude it from training, i.e. its weights will never be updated. This is useful in the context of fine-tuning a model, or using fixed embeddings for a text input. You can pass a `trainable` argument (boolean) to a layer constructor to set a layer to be non-trainable: ```python frozen_layer = Dense(32, trainable=False) ``` Additionally, you can set the `trainable` property of a layer to `True` or `False` after instantiation. For this to take effect, you will need to call `compile()` on your model after modifying the `trainable` property. Here's an example: """ from tensorflow.contrib.keras.python.keras.layers import Input, Dense from tensorflow.contrib.keras.python.keras.models import Model import numpy as np input_tensor = Input(shape=(32, )) layer = Dense(5) layer.trainable = False tensor_no_train = layer(input_tensor) frozen_model = Model(input_tensor, tensor_no_train) # in the model below, the weights of `layer` will not be updated during training frozen_model.compile(optimizer='rmsprop', loss='mse') layer.trainable = True tensor_do_train = layer(input_tensor) trainable_model = Model(input_tensor, tensor_do_train) # with this model the weights of the layer will be updated during training # (which will also affect the above model since it uses the same layer instance) trainable_model.compile(optimizer='rmsprop', loss='mse')
- middle_layer_tensor = K.function([input_tensor, K.learning_phase()], [output_tensor])([input_array, 1])[0] # for train mode
"""
"""
todo: K.learning_phase()???
One simple way is to create a new `Model` that will output the layers that you are interested in:
"""
from tensorflow.contrib.keras.python.keras.models import Model, Sequential
from tensorflow.contrib.keras.python.keras.layers import Input, Dense
from tensorflow.contrib.keras.python.keras import backend as K
import numpy as np
input_tensor = Input(shape=(100, ), name="input_tensor")
inter_tensor = Dense(30, name="my_layer")(input_tensor)
final_tensor = Dense(30, name="final_layer")(inter_tensor)
model = Model(input_tensor, final_tensor) # create the original model
layer_name = 'my_layer'
intermediate_layer_model = Model(inputs=model.input,
outputs=model.get_layer(layer_name).output)
# must compile before predict? No, but must compile before training
input_array1 = np.random.random((1000, 100)) * 9
input_tensor1 = K.constant(value=input_array1)
intermediate_output = intermediate_layer_model.predict(
input_array1) # return array
intermediate_output1 = intermediate_layer_model(
input_tensor1
if 'bg' not in class_mapping:
class_mapping['bg'] = len(class_mapping)
class_mapping = {v: k for k, v in list(class_mapping.items())}
print(class_mapping)
class_to_color = {
class_mapping[v]: np.random.randint(0, 255, 3)
for v in class_mapping
}
C.num_rois = int(options.num_rois)
input_shape_img = (None, None, 3)
input_shape_features = (None, None, 1024)
img_input = Input(shape=input_shape_img)
roi_input = Input(shape=(C.num_rois, 4))
feature_map_input = Input(shape=input_shape_features)
# define the base network (resnet here, can be VGG, Inception, etc)
shared_layers = nn.nn_base(img_input, trainable=True)
# define the RPN, built on the base layers
num_anchors = len(C.anchor_box_scales) * len(C.anchor_box_ratios)
rpn_layers = nn.rpn(shared_layers, num_anchors)
classifier = nn.classifier(feature_map_input,
roi_input,
C.num_rois,
nb_classes=len(class_mapping),
trainable=True)
train, train_label, test, test_label \
= make_data(train_mat = "train_foot2.mat",
test_mat = "test_foot2.mat",
train_label_mat = "label_foot.mat",
test_label_mat = "label_foot.mat",
seq_len=seq_len)
N_train = len(train)
vector_dim = train.shape[2]
train = train.reshape(-1, seq_len, vector_dim, 1)
test = test.reshape(-1, seq_len, vector_dim, 1)
'''
construction model
'''
inputs = Input(shape=(train.shape[1:]))
x = Conv2D(16, (8, 1), padding='same', use_bias=False)(inputs)
x = Conv2D(16, (8, 1), padding='same', use_bias=False, activation='relu')(x)
x = BatchNormalization(axis=1)(x)
x = Dropout(0.3)(x)
x = Conv2D(32, (8, 1), padding='same', use_bias=False)(inputs)
x = Conv2D(32, (8, 1), padding='same', use_bias=False, activation='relu')(x)
x = BatchNormalization(axis=1)(x)
x = Dropout(0.3)(x)
x = Conv2D(64, (8, 1), padding='same', use_bias=False)(inputs)
x = Conv2D(64, (8, 1), padding='same', use_bias=False, activation='relu')(x)
x = BatchNormalization(axis=1)(x)
x = Dropout(0.3)(x)
# note that we set trainable = False so as to keep the embeddings fixed
embedding_layer = Embedding(
num_words, # only use 20000 words out of 400000 vocabularies
EMBEDDING_DIM, # each word has a vector of 100 dim
weights=[
embedding_matrix
], # only take weights of words (20000, 100), out of (400000, 100)
input_length=
MAX_SEQUENCE_LENGTH, # max length of a sample text, 1000; a text is no longer than 1000 words
trainable=False) # keep embedding weights fixed
print('Training model.')
# train a 1D convnet with global maxpooling
sequence_input = Input(
shape=(MAX_SEQUENCE_LENGTH, ), dtype='int32'
) # (?, 1000) build placeholder for texts with any number of samples, 1000 in length each
embedded_sequences = embedding_layer(
sequence_input
) # output tensor is (?, text_input_length, embedding_dim) == (?, 1000, 100) == each sample text has 1000 words to describe, each word has 100 dims to describe
x = Conv1D(128, 5, activation='relu')(
embedded_sequences
) # (?, 996, 128), 996== 1000-4; 1D convolution layer (e.g. temporal convolution). This layer creates a convolution kernel that is convolved with the layer input over a single spatial (or temporal) dimension to produce a tensor of outputs. # maybe, Conv1D is like a single vector or one line of 5 pixel screener, moving from left to right, and from row to row
# conv1d_t1 = x
x = MaxPooling1D(5)(x) # (?, 199, 128), 199=(996-1)/5
# maxp_t1 = x
x = Conv1D(128, 5, activation='relu')(x) # (?, 195, 128), 195=199-4
# conv1d_t2 = x
x = MaxPooling1D(5)(x) # (?, 39, 128), 39 == 195/5
# maxp_t2 = x
x = Conv1D(128, 5, activation='relu')(x) # (?, 35, 128)
'Arguments:\n'
' shape: Shape of the placeholder\n'
' (integer tuple, may include `None` entries).\n'
' ndim: Number of axes of the tensor.\n'
' At least one of {`shape`, `ndim`} must be specified.\n'
' If both are specified, `shape` is used.\n'
' dtype: Placeholder type.\n'
' sparse: Boolean, whether the placeholder should have a sparse type.\n'
' name: Optional name string for the placeholder.\n'
'\n'
'Returns:\n'
' Tensor instance (with Keras metadata included).\n'
'\n'
"""
# tensor = K.constant, return a constant tensor
input_tensor = Input(tensor=input)
# tensor = K.placeholder, return a placeholder tensor
input_tensor1 = Input(tensor=input_placeholder1)
# tensor = K.placeholder, return a placeholder tensor
input_tensor2 = Input(tensor=input_placeholder2)
# shape is set, then num_samples is ? or arbitrary
input_tensor3 = Input(shape=input_placeholder1.shape)
# batch_shape is set, then num_samples is specified
input_tensor4 = Input(batch_shape=input_placeholder2.shape)
"""
Inputs:
- shape, batch_shape, tensor, one of them must be given
- tensor:
"""
### Residual connection on a convolution layer
For more information about residual networks, see [Deep Residual Learning for Image Recognition](http://arxiv.org/abs/1512.03385).
"""
from tensorflow.contrib.keras.python.keras.layers import add, Input, Conv2D
from tensorflow.contrib.keras.python.keras.models import Model
# input tensor for a 3-channel 256x256 image
# x = Input(shape=(3, 256, 256)) will cause error
x = Input(shape=(256, 256, 3))
# due to keras.backend._config uses channels_last
# 3x3 conv with 3 output channels (same as input channels)
y = Conv2D(3, (3, 3), padding='same')(x)
# this returns x + y.
z = add(
[x, y]
) # take in same shape input tensor list, return same shape tensor, in order words, add([x,y]) is row-bind
model = Model(x, z)
model.summary()
def nn_base(input_tensor=None, trainable=False):
# Determine proper input shape
input_shape = (None, None, 3)
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
if not is_keras_tensor(input_tensor):
img_input = Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
bn_axis = 3
x = ZeroPadding2D((3, 3))(img_input)
x = Convolution2D(64, (7, 7),
strides=(2, 2),
name='conv1',
trainable=trainable)(x)
x = FixedBatchNormalization(axis=bn_axis, name='bn_conv1')(x)
x = Activation('relu')(x)
x = MaxPooling2D((3, 3), strides=(2, 2))(x)
x = conv_block(x,
3, [64, 64, 256],
stage=2,
block='a',
strides=(1, 1),
trainable=trainable)
x = identity_block(x,
3, [64, 64, 256],
stage=2,
block='b',
trainable=trainable)
x = identity_block(x,
3, [64, 64, 256],
stage=2,
block='c',
trainable=trainable)
x = conv_block(x,
3, [128, 128, 512],
stage=3,
block='a',
trainable=trainable)
x = identity_block(x,
3, [128, 128, 512],
stage=3,
block='b',
trainable=trainable)
x = identity_block(x,
3, [128, 128, 512],
stage=3,
block='c',
trainable=trainable)
x = identity_block(x,
3, [128, 128, 512],
stage=3,
block='d',
trainable=trainable)
x = conv_block(x,
3, [256, 256, 1024],
stage=4,
block='a',
trainable=trainable)
x = identity_block(x,
3, [256, 256, 1024],
stage=4,
block='b',
trainable=trainable)
x = identity_block(x,
3, [256, 256, 1024],
stage=4,
block='c',
trainable=trainable)
x = identity_block(x,
3, [256, 256, 1024],
stage=4,
block='d',
trainable=trainable)
x = identity_block(x,
3, [256, 256, 1024],
stage=4,
block='e',
trainable=trainable)
x = identity_block(x,
3, [256, 256, 1024],
stage=4,
block='f',
trainable=trainable)
return x
def MobileNet(
input_shape=None, # pylint: disable=invalid-name
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 input 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.
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 [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 [0.25, 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 main():
training_images, training_labels, test_images, test_labels = load_dataset()
# plt.imshow(training_images[:,:,0], cmap='gray')
# plt.show()
perm_train = np.random.permutation(training_labels.size)
training_labels = training_labels[perm_train]
training_images = (training_images[perm_train, :, :] - 127.5) / 127.5
training_images = np.expand_dims(training_images, -1)
print(training_images.shape)
test_images = test_images / 255.0
test_images = np.expand_dims(test_images, -1)
# pdb.set_trace()
# training_labels = to_categorical(training_labels, NUM_CLASSES)
# test_labels = to_categorical(test_labels, NUM_CLASSES)
BATCH_SIZE = 32 * 8
WIDTH, HEIGHT = 28, 28
adam_lr = 0.0002
adam_beta_1 = 0.5
#####################################
### Defiining the Discriminator:
#####################################
input_D = Input(shape=(HEIGHT, WIDTH, 1), name='input_D')
x = Conv2D(filters=32,
kernel_size=3,
strides=(2, 2),
padding='same',
name='conv1_D')(input_D)
#x = BatchNormalization()(x)
x = Activation('relu')(x)
x = Conv2D(filters=32,
kernel_size=3,
strides=(2, 2),
padding='same',
name='conv2_D')(x)
#x = BatchNormalization()(x)
x = Activation('relu')(x)
x = Flatten()(x)
x = Dense(128, activation='relu', name='dense1_D')(x)
output_D = Dense(1, activation='sigmoid', name='output_D')(x)
model_D = Model(inputs=input_D, outputs=output_D)
model_D.compile(loss='binary_crossentropy',
optimizer=tf.train.AdamOptimizer(learning_rate=adam_lr,
beta1=adam_beta_1),
metrics=['accuracy'])
#####################################
### Defiining the Generator:
#####################################
LATENT_SIZE = 100
input_G = Input(shape=(LATENT_SIZE, ), name='input_gen')
x = Dense(7 * 7 * 32, activation='linear', name='Dense1_G')(input_G)
x = BatchNormalization()(x)
x = Activation('relu')(x)
x = Reshape((7, 7, 32))(x)
x = UpSampling2D((2, 2))(x)
x = Conv2D(filters=32,
kernel_size=3,
strides=(1, 1),
padding='same',
name='conv1_gen')(x)
x = BatchNormalization()(x)
x = Activation('relu')(x)
x = UpSampling2D((2, 2))(x)
x = Conv2D(filters=32,
kernel_size=3,
strides=(1, 1),
padding='same',
name='conv2_gen')(x)
x = BatchNormalization()(x)
x = Activation('relu')(x)
x = Conv2D(filters=1,
kernel_size=1,
strides=(1, 1),
padding='same',
name='conv3_gen')(x)
img_G = Activation('tanh')(x)
model_G = Model(inputs=input_G, outputs=img_G)
model_G.compile(loss='binary_crossentropy',
optimizer=tf.train.AdamOptimizer(learning_rate=adam_lr,
beta1=adam_beta_1))
#####################################
### Defiining the Combined GAN:
#####################################
model_D.trainable = False # Since model_D is already compiled, thediscriminator model remains trainble,
# but here in the combined model it becomes non-trainable
input_main = Input(
shape=(LATENT_SIZE, ), name='input_main'
) # Note that this input should be different from the input to Generator
combined = Model(inputs=input_main, outputs=model_D(model_G(input_main)))
combined.compile(loss='binary_crossentropy',
optimizer=tf.train.AdamOptimizer(learning_rate=adam_lr,
beta1=adam_beta_1),
metrics=['accuracy'])
print(combined.summary())
#####################################
### Training:
#####################################
bar = InitBar()
N = training_images.shape[0]
for iter in range(100):
fake_input = np.random.randn(1, LATENT_SIZE)
fake_image = model_G.predict(fake_input)
loss_G, acc_G, loss_D, acc_D = 0, 0, 0, 0
steps = (int)(np.ceil(float(N) / float(BATCH_SIZE)))
for batch_iter in range(steps):
bar(100.0 * batch_iter / float(steps))
real_image, _ = get_batch(batch_iter, BATCH_SIZE / 2,
training_images, training_labels)
####################
## Discriminator Training
####################
# Note that if using BN layer in Discriminator, minibatch should contain only real images or fake images.
fake_input = np.random.randn(BATCH_SIZE / 2, LATENT_SIZE)
fake_image = model_G.predict(fake_input)
#real_image = get_real_mbatch(batch_sz=BATCH_SIZE/2, data=training_images)
agg_input = np.concatenate((fake_image, real_image), axis=0)
agg_output = np.zeros((BATCH_SIZE, ))
agg_output[BATCH_SIZE / 2:] = 1
perm = np.random.permutation(BATCH_SIZE)
agg_input = agg_input[perm]
agg_output = agg_output[perm]
#pdb.set_trace()
tr = model_D.train_on_batch(x=agg_input, y=agg_output)
loss_D += tr[0]
acc_D += tr[1]
#####################
## Generator Training
#####################
fake_input = np.random.randn(BATCH_SIZE, LATENT_SIZE)
fake_label = np.ones(BATCH_SIZE, )
tr = combined.train_on_batch(x=fake_input, y=fake_label)
loss_G += tr[0]
acc_G += tr[1]
print('\nG_loss = {}, G_acc = {}\nD_loss = {}, D_acc = {}'.format(
loss_G / float(steps), acc_G / float(steps), loss_D / float(steps),
acc_D / float(steps)))
for iter in range(10):
fake_input = np.random.randn(1, LATENT_SIZE)
fake_image = model_G.predict(fake_input)
plt.imshow(fake_image[0, :, :, 0])
plt.show()
def build_network(args, data):
max_sentence_len = data["train_word"][0].shape[1]
max_word_len = data["char"][0].shape[-1] / max_sentence_len
num_labels = data["label_collection"].size() - 1
# Input tensor contains char indices
# for all words in a given batch of sentences
# Shape: batch_size, max_sentence_len * max_word_len
char_input = Input(shape=(max_sentence_len * max_word_len, ),
name="char_input",
dtype="int32")
# 3D tensor containing char based word embeddings
# for the given batch of sentences
# Shape: batch_size, max_sentence_len, num_filters
char_based_word_emb = get_char_based_embeddings(args, data, char_input,
"char")
# Input tensor containing word indices
# for the given batch of sentences
# Shape: batch_size, max_sentence_len
word_input = Input(shape=(max_sentence_len, ),
name="word_input",
dtype="int32")
# 3D tensor containing word embeddings
# for the given batch of sentences
# Shape: batch_size, max_sentence_len, word_emb_dim
word_emb = get_word_embeddings(args, data, word_input, "word")
# Input tensor contains orth char indices
# for all words in a given batch of sentences
# Shape: batch_size, max_sentence_len * max_word_len
orth_char_input = Input(shape=(max_sentence_len * max_word_len, ),
name="orth_char_input",
dtype="int32")
# 3D tensor containing orth char based word embeddings
# for the given batch of sentences
# Shape: batch_size, max_sentence_len, num_filters
orth_char_based_word_emb = get_char_based_embeddings(
args, data, orth_char_input, "orth_char")
# Input tensor containing orth word indices
# for the given batch of sentences
# Shape: batch_size, max_sentence_len
orth_word_input = Input(shape=(max_sentence_len, ),
name="orth_word_input",
dtype="int32")
# 3D tensor containing orth word embeddings
# for the given batch of sentences
# Shape: batch_size, max_sentence_len, orth_word_emb_dim
orth_word_emb = get_word_embeddings(args, data, orth_word_input,
"orth_word")
inputs = [
char_based_word_emb, word_emb, orth_char_based_word_emb, orth_word_emb
]
bi_lstm_output = get_bi_lstm_output(args, data, inputs)
lstm_output_dim = bi_lstm_output.shape[2]
hidden_layer_output = TimeDistributed(
Dense(units=num_labels,
input_shape=(max_sentence_len, lstm_output_dim)))(bi_lstm_output)
crf_output = ChainCRF(name="output")(hidden_layer_output)
model = Model(
inputs=[char_input, word_input, orth_char_input, orth_word_input],
outputs=crf_output)
# model = Model(
# inputs=[char_input, word_input, orth_char_input, orth_word_input],
# outputs=bi_lstm_output)
# model.summary()
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)
# 10x block8 (Inception-ResNet-C block): 8 x 8 x 2080
for block_idx in range(1, 10):
x = inception_resnet_block(x,
scale=0.2,
block_type='block8',
block_idx=block_idx)
x = inception_resnet_block(x,
scale=1.,
activation=None,
block_type='block8',
block_idx=10)
# Final convolution block: 8 x 8 x 1536
x = conv2d_bn(x, 1536, 1, name='conv_7b')
if include_top:
# Classification block
x = GlobalAveragePooling2D(name='avg_pool')(x)
x = Dense(classes, activation='softmax', name='predictions')(x)
else:
if pooling == 'avg':
x = GlobalAveragePooling2D()(x)
elif pooling == 'max':
x = GlobalMaxPooling2D()(x)
# Ensure that the model takes into account
# any potential predecessors of `input_tensor`
if input_tensor is not None:
inputs = get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model
model = Model(inputs, x, name='inception_resnet_v2')
# Load weights
if weights == 'imagenet':
if K.image_data_format() == 'channels_first':
if K.backend() == 'tensorflow':
warnings.warn('You are using the TensorFlow backend, yet you '
'are using the Theano '
'image data format convention '
'(`image_data_format="channels_first"`). '
'For best performance, set '
'`image_data_format="channels_last"` in '
'your Keras config '
'at ~/.keras/keras.json.')
if include_top:
weights_filename = 'inception_resnet_v2_weights_tf_dim_ordering_tf_kernels.h5'
weights_path = get_file(
weights_filename,
BASE_WEIGHT_URL + weights_filename,
cache_subdir='models',
file_hash='e693bd0210a403b3192acc6073ad2e96')
else:
weights_filename = 'inception_resnet_v2_weights_tf_dim_ordering_tf_kernels_notop.h5'
weights_path = get_file(
weights_filename,
BASE_WEIGHT_URL + weights_filename,
cache_subdir='models',
file_hash='d19885ff4a710c122648d3b5c3b684e4')
model.load_weights(weights_path)
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 input 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:
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 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)
return model
def main():
training_images, training_labels, test_images, test_labels = load_dataset()
# plt.imshow(training_images[:,:,0], cmap='gray')
# plt.show()
N = training_labels.size
Nt = test_labels.size
perm_train = np.random.permutation(N)
training_labels = training_labels[perm_train]
training_images = training_images[perm_train, :, :] / 255.0
training_images = np.expand_dims(training_images, -1)
print(training_images.shape)
test_images = test_images / 255.0
test_images = np.expand_dims(test_images, -1)
# pdb.set_trace()
training_labels = to_categorical(training_labels, NUM_CLASSES)
test_labels = to_categorical(test_labels, NUM_CLASSES)
BATCH_SIZE = 32 * 8
WIDTH, HEIGHT = 28, 28
epochs = 30
# Defiining the placeholders
input_data = tf.placeholder(dtype=tf.float32,
shape=[None, HEIGHT, WIDTH, 1],
name='data')
input_labels = tf.placeholder(dtype=tf.float32,
shape=[None, NUM_CLASSES],
name='labels')
do_rate = tf.placeholder(dtype=tf.float32, name='dropout_rate')
# pdb.set_trace()
with tf.name_scope('conv1'):
with tf.variable_scope('conv1'):
W_conv1 = tf.get_variable('w', [3, 3, 1, 32])
b_conv1 = tf.get_variable('b', [32])
conv1 = tf.nn.conv2d(input=input_data,
filter=W_conv1,
strides=[1, 1, 1, 1],
padding='SAME')
relu1 = tf.nn.relu(conv1 + b_conv1)
with tf.name_scope('pool1'):
pool1 = tf.nn.max_pool(value=relu1,
ksize=[1, 2, 2, 1],
strides=[1, 2, 2, 1],
padding='SAME')
with tf.name_scope('conv2'):
with tf.variable_scope('conv2'):
W_conv2 = tf.get_variable('w', [3, 3, 32, 32])
b_conv2 = tf.get_variable('b', [32])
conv2 = tf.nn.conv2d(input=pool1,
filter=W_conv2,
strides=[1, 1, 1, 1],
padding='VALID')
relu2 = tf.nn.relu(conv2 + b_conv2)
with tf.name_scope('pool2'):
pool2 = tf.nn.max_pool(value=relu2,
ksize=[1, 2, 2, 1],
strides=[1, 2, 2, 1],
padding='SAME')
with tf.name_scope('dense1'):
with tf.variable_scope('dense1'):
W_dense1 = tf.get_variable('w', [6 * 6 * 32, 128])
b_dense1 = tf.get_variable('b', 128)
flat = tf.reshape(pool2, [-1, 6 * 6 * 32], name='reshape')
dense1 = tf.matmul(flat, W_dense1)
relu3 = tf.nn.relu(dense1 + b_dense1)
with tf.name_scope('dropout'):
dropout = tf.nn.dropout(relu3, do_rate)
with tf.name_scope('output'):
with tf.variable_scope('output'):
W_out = tf.get_variable('w', [128, NUM_CLASSES])
b_out = tf.get_variable('b', [NUM_CLASSES])
output = tf.matmul(dropout, W_out) + b_out
'''
################################################################
""" Using Keras layers instead """
#input_layer = Input(shape=(HEIGHT, WIDTH, 1), name='input_layer')
Kcnn1 = Conv2D(filters=32, kernel_size=3, strides=(1,1), padding='same', activation='relu')(input_data)
Kmaxpool1 = MaxPooling2D(pool_size=2)(Kcnn1)
Kcnn2 = Conv2D(filters=32, kernel_size=3, strides=(1,1), padding='valid', activation='relu')(Kmaxpool1)
Kmaxpool2 = MaxPooling2D(pool_size=2)(Kcnn2)
Kflat = Flatten()(Kmaxpool2)
Kdense1 = Dense(units=128, activation='relu')(Kflat)
Kdropout = Dropout(.5)(Kdense1)
output = Dense(units=NUM_CLASSES, activation='softmax')(Kdropout)
""" The rest of the code is almost the same as in pure_tf_mnist.py,
except for the feed_dict, where instead of do_rate in tensorflow,
we need to provide keras specific dropout tensor 'learning_phase'
in the backend of Keras. """
################################################################
'''
print('\n\n')
print('-------------------------------------------------------')
print('--------------- Trainable parameters ------------------')
print('-------------------------------------------------------')
total_parameters = 0
for v in tf.trainable_variables():
shape = v.get_shape()
print(shape)
#pdb.set_trace()
params = 1
for dim in shape:
params *= dim.value
total_parameters += params
print('total_parameters = {}'.format(total_parameters))
print('-------------------------------------------------------\n\n')
loss = tf.reduce_mean(
tf.nn.softmax_cross_entropy_with_logits(labels=input_labels,
logits=output,
name='loss'))
train_op = tf.train.AdamOptimizer(1e-4).minimize(loss)
accuracy = tf.cast(
tf.equal(tf.argmax(input_labels, 1), tf.argmax(output, 1)), tf.float32)
print('')
print('-------------------------------------------------------')
print('---------- Starting a TF session ----------------------')
print('-------------------------------------------------------')
print('')
tf_weights = []
tf.set_random_seed(1234)
# Training:
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
writer = tf.summary.FileWriter('graph', sess.graph)
print('-------------------------------------------------------')
print('--------------- Training phase ------------------------')
print('-------------------------------------------------------')
for i in range(epochs):
steps = (int)(np.ceil(float(N) / float(BATCH_SIZE)))
total_l = 0
total_acc = 0
for step in range(steps):
x_in, y_in = get_batch(step, BATCH_SIZE, training_images,
training_labels)
l, acc, _ = sess.run([loss, accuracy, train_op], {
input_data: x_in,
input_labels: y_in,
do_rate: 0.5
})
total_l += l
total_acc += np.sum(acc)
#pdb.set_trace()
total_acc /= np.float32(N)
print(
"Epoch {}: Training loss = {}, Training accuracy = {}".format(
i, total_l, total_acc))
# Test:
total_acc = 0
steps = (int)(np.ceil(float(Nt) / float(BATCH_SIZE)))
for step in range(steps):
x_in, y_in = get_batch(step, BATCH_SIZE, test_images, test_labels)
acc = sess.run([accuracy], {
input_data: x_in,
input_labels: y_in,
do_rate: 1
})
total_acc += np.sum(acc)
total_acc /= np.float32(Nt)
print('\n-----------------------')
print("Test accuracy = {}".format(total_acc))
print('-------------------------------------------------------')
#################################################################
### Exporting the trained weights into a list of numpy vectors
for v in tf.trainable_variables():
tf_weights.append(sess.run(v))
writer.close()
print('')
print('-------------------------------------------------------')
print('---------- Starting a Keras session -------------------')
print('-------------------------------------------------------')
print('')
#################################################################
""" Building a Keras Model """
input_layer = Input(shape=(HEIGHT, WIDTH, 1), name='input_layer')
Kkcnn1 = Conv2D(filters=32,
kernel_size=3,
strides=(1, 1),
padding='same',
activation='relu')(input_layer)
Kkmaxpool1 = MaxPooling2D(pool_size=2)(Kkcnn1)
Kkcnn2 = Conv2D(filters=32,
kernel_size=3,
strides=(1, 1),
padding='valid',
activation='relu')(Kkmaxpool1)
Kkmaxpool2 = MaxPooling2D(pool_size=2)(Kkcnn2)
Kkflat = Flatten()(Kkmaxpool2)
Kkdense1 = Dense(units=128, activation='relu')(Kkflat)
Kkdropout = Dropout(.5)(Kkdense1)
output_layer = Dense(units=NUM_CLASSES, activation='softmax')(Kkdropout)
model = Model(inputs=input_layer, outputs=output_layer)
model.compile(optimizer=tf.train.AdamOptimizer(),
loss='categorical_crossentropy',
metrics=['accuracy'])
#################################################################
#################################################################
### Loarding the already trained weights, onto the keras layers
c = 0 # counter for iterating over tensorflow trainable variables
#pdb.set_trace()
for l in model.layers:
trainable_weights = l.trainable_weights
if not trainable_weights:
# empty trainable weight list in this keras layer; so move on to the next layer.
continue
len_w = len(
trainable_weights
) # e.g. for a normal conv layer, it is two: weight and bias.
l.set_weights(tf_weights[c:c + len_w])
c += len_w
accuracy = model.evaluate(x=test_images,
y=test_labels,
batch_size=BATCH_SIZE)
print('\n')
print('Keras test score = {}'.format(accuracy))
print('\n')
def main():
training_images, training_labels, test_images, test_labels = load_dataset()
# plt.imshow(training_images[:,:,0], cmap='gray')
# plt.show()
perm_train = np.random.permutation(training_labels.size)
training_labels = training_labels[perm_train]
training_images = training_images[perm_train, :, :] / 255.0
training_images = np.expand_dims(training_images, -1)
print(training_images.shape)
test_images = test_images / 255.0
test_images = np.expand_dims(test_images, -1)
# pdb.set_trace()
# training_labels = to_categorical(training_labels, NUM_CLASSES)
# test_labels = to_categorical(test_labels, NUM_CLASSES)
BATCH_SIZE = 32 * 8
WIDTH, HEIGHT = 28, 28
# Defiining the network
input_layer = Input(shape=(HEIGHT, WIDTH, 1), name='input_layer')
cnn1 = Conv2D(filters=32,
kernel_size=3,
strides=(1, 1),
padding='same',
activation='relu')(input_layer)
maxpool = MaxPooling2D(pool_size=2)(cnn1)
cnn2 = Conv2D(filters=32,
kernel_size=3,
strides=(1, 1),
padding='valid',
activation='relu')(maxpool)
maxpool = MaxPooling2D(pool_size=2)(cnn2)
flat = Flatten()(maxpool)
dense1 = Dense(units=128, activation='relu')(flat)
dropout = Dropout(.5)(dense1)
output_layer = Dense(units=NUM_CLASSES, activation='softmax')(dropout)
model = Model(inputs=input_layer, outputs=output_layer)
model.compile(optimizer=tf.train.AdamOptimizer(),
loss='sparse_categorical_crossentropy',
metrics=['accuracy'])
# pdb.set_trace()
print(model.summary())
model.fit(x=training_images,
y=training_labels,
batch_size=BATCH_SIZE,
epochs=30,
verbose=1,
validation_data=(test_images, test_labels))
accuracy = model.evaluate(x=test_images,
y=test_labels,
batch_size=BATCH_SIZE)
print('test score = {}'.format(accuracy))
- train_on_batch() and test_on_batch() is to train or test the whole dataset at once (no matter how big they are)
- model.fit(batch_size), model.fit_generator() are to train a small batch at a time until all dataset are trained
"""
from tensorflow.contrib.keras.python.keras.layers import Dropout, BatchNormalization, Input, Dense
from tensorflow.contrib.keras.python.keras.models import Model
import numpy as np
from tensorflow.contrib.keras.python.keras import backend as K
from tensorflow.contrib.keras.python.keras import losses
x = np.random.random((10, 10)) * 2
y = np.random.randint(2, size=(10, 1))
input_tensor = Input(shape=(10, ))
bn_tensor = BatchNormalization()(input_tensor)
dp_tensor = Dropout(0.7)(bn_tensor)
final_tensor = Dense(1)(dp_tensor)
model = Model(input_tensor, final_tensor)
model.compile(optimizer='SGD', loss='mse')
# x, y won't get into batches for training here
loss_on_batch = model.train_on_batch(x, y) # dive in for details
"""
('Runs a single gradient update on a single batch of data.\n'
'\n'
'Arguments:\n'
' x: Numpy array of training data,\n'
' or list of Numpy arrays if the model has multiple inputs.\n'
def VGG16(include_top=True,
weights='imagenet',
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000):
"""Instantiates the VGG16 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, 224)` (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:
img_input = Input(tensor=input_tensor, shape=input_shape)
# Block 1
x = Conv2D(64, (3, 3),
activation='relu',
padding='same',
name='block1_conv1')(img_input)
x = Conv2D(64, (3, 3),
activation='relu',
padding='same',
name='block1_conv2')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='block1_pool')(x)
# Block 2
x = Conv2D(128, (3, 3),
activation='relu',
padding='same',
name='block2_conv1')(x)
x = Conv2D(128, (3, 3),
activation='relu',
padding='same',
name='block2_conv2')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='block2_pool')(x)
# Block 3
x = Conv2D(256, (3, 3),
activation='relu',
padding='same',
name='block3_conv1')(x)
x = Conv2D(256, (3, 3),
activation='relu',
padding='same',
name='block3_conv2')(x)
x = Conv2D(256, (3, 3),
activation='relu',
padding='same',
name='block3_conv3')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='block3_pool')(x)
# Block 4
x = Conv2D(512, (3, 3),
activation='relu',
padding='same',
name='block4_conv1')(x)
x = Conv2D(512, (3, 3),
activation='relu',
padding='same',
name='block4_conv2')(x)
x = Conv2D(512, (3, 3),
activation='relu',
padding='same',
name='block4_conv3')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='block4_pool')(x)
# Block 5
x = Conv2D(512, (3, 3),
activation='relu',
padding='same',
name='block5_conv1')(x)
x = Conv2D(512, (3, 3),
activation='relu',
padding='same',
name='block5_conv2')(x)
x = Conv2D(512, (3, 3),
activation='relu',
padding='same',
name='block5_conv3')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='block5_pool')(x)
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='vgg16')
# load weights
if weights == 'imagenet':
if include_top:
weights_path = get_file(
'vgg16_weights_tf_dim_ordering_tf_kernels.h5',
WEIGHTS_PATH,
cache_subdir='models')
else:
weights_path = get_file(
'vgg16_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
dprint('Num train samples {}'.format(len(train_imgs)))
dprint('Num val samples {}'.format(len(val_imgs)))
data_gen_train = data_generators.get_anchor_gt(train_imgs,
classes_count,
C,
mode='train')
data_gen_val = data_generators.get_anchor_gt(val_imgs,
classes_count,
C,
mode='val')
input_shape_img = (None, None, 3)
img_input = Input(shape=input_shape_img)
roi_input = Input(shape=(C.num_rois, 4))
# define the base network (resnet here, can be VGG, Inception, etc)
shared_layers = nn.nn_base(img_input, trainable=True)
# define the RPN, built on the base layers
num_anchors = len(C.anchor_box_scales) * len(C.anchor_box_ratios)
rpn = nn.rpn(shared_layers, num_anchors)
classifier = nn.classifier(shared_layers,
roi_input,
C.num_rois,
nb_classes=len(classes_count),
trainable=True)
