def _copy_layer(layer):
# Whenever the network config attempts to get the layer serialization,
# return a dummy dictionary.
if layer in input_layers:
created_layers[layer.name] = input_layers[layer]
elif layer in model._input_layers:
created_layers[layer.name] = InputLayer(**layer.get_config())
else:
created_layers[layer.name] = layer_fn(layer)
return {}
def get_model(img_res, num_img_per_seq, num_cls, selected_model='CNN+RNN'):
if selected_model == 'CNN+RNN':
model = Sequential()
model.add(InputLayer(input_shape=(num_img_per_seq, img_res[0], img_res[1], 3)))
model.add(TimeDistributed(Convolution2D(32, (4, 4), activation='relu')))
model.add(TimeDistributed(MaxPooling2D(pool_size=(5, 5))))
model.add(TimeDistributed(Convolution2D(16, (4, 4), activation='relu')))
model.add(TimeDistributed(MaxPooling2D(pool_size=(5, 5))))
model.add(TimeDistributed(Dropout(0.25)))
model.add(TimeDistributed(Flatten()))
model.add(GRU(128, kernel_initializer=initializers.RandomNormal(stddev=0.001))) # 128
model.add(Dropout(0.25))
model.add(Dense(60))
model.add(Dense(40))
model.add(Dense(num_cls, activation='sigmoid'))
opt = optimizers.RMSprop(lr=0.001)
model.compile(loss='mean_squared_error', optimizer=opt, metrics=['accuracy'])
return model
elif selected_model == 'CNN+MLP':
model = Sequential()
model.add(InputLayer(input_shape=(num_img_per_seq, img_res[0], img_res[1], 3)))
model.add(TimeDistributed(Convolution2D(32, (4, 8), activation='relu')))
model.add(TimeDistributed(Convolution2D(16, (4, 4), activation='relu')))
model.add(TimeDistributed(MaxPooling2D(pool_size=(5, 5))))
model.add(TimeDistributed(Dropout(0.25)))
model.add(Flatten())
model.add(Dense(60))
model.add(Dense(80))
model.add(Dense(num_cls, activation='sigmoid'))
opt = optimizers.RMSprop(lr=0.001)
model.compile(loss='mean_squared_error', optimizer=opt, metrics=['accuracy'])
return model
def get_dense_networks(args: Arguments):
networks = get_networks('mnist',
is_semi_supervised=False,
is_hierarchical=False,
zdim=args.zdim)
networks['encoder'] = SequentialNetwork([
InputLayer(input_shape=[28, 28, 1]),
CenterAt0(),
Flatten(),
Dense(1024, activation='relu'),
Dense(1024, activation='relu'),
Dense(1024, activation='relu'),
],
name='Encoder')
networks['decoder'] = SequentialNetwork([
InputLayer(input_shape=[args.zdim]),
Dense(1024, activation='relu'),
Dense(1024, activation='relu'),
Dense(1024, activation='relu'),
Dense(28 * 28 * 1, activation='linear'),
Reshape([28, 28, 1]),
],
name='Decoder')
return networks
def __init__(self):
model = Sequential()
model.add(InputLayer(input_shape=(None, None, 1)))
model.add(Conv2D(8, (3, 3), activation='relu', padding='same', strides=2))
model.add(Conv2D(8, (3, 3), activation='relu', padding='same'))
model.add(Conv2D(16, (3, 3), activation='relu', padding='same'))
model.add(Conv2D(16, (3, 3), activation='relu', padding='same', strides=2))
model.add(Conv2D(32, (3, 3), activation='relu', padding='same'))
model.add(Conv2D(32, (3, 3), activation='relu', padding='same', strides=2))
model.add(UpSampling2D((2, 2)))
model.add(Conv2D(32, (3, 3), activation='relu', padding='same'))
model.add(UpSampling2D((2, 2)))
model.add(Conv2D(16, (3, 3), activation='relu', padding='same'))
model.add(UpSampling2D((2, 2)))
model.add(Conv2D(2, (3, 3), activation='tanh', padding='same'))
model.compile(optimizer='rmsprop', loss='mse')
self.model = model
def __init__(self):
# Design the neural network
model = Sequential()
model.add(InputLayer(input_shape=(256, 256, 1)))
#model.add(Conv2D(64, (2, 2), activation='relu', padding='same'))
#model.add(Conv2D(64, (4, 4), activation='relu', padding='same'))
model.add(Conv2D(64, (3, 3), activation='relu', padding='same'))
model.add(Conv2D(64, (3, 3), activation='relu', padding='same', strides=2))
model.add(Conv2D(128, (3, 3), activation='relu', padding='same'))
model.add(Conv2D(128, (3, 3), activation='relu', padding='same', strides=2))
model.add(Conv2D(256, (3, 3), activation='relu', padding='same'))
model.add(Conv2D(256, (3, 3), activation='relu', padding='same', strides=2))
model.add(Conv2D(512, (3, 3), activation='relu', padding='same'))
model.add(Conv2D(256, (3, 3), activation='relu', padding='same'))
model.add(Conv2D(128, (3, 3), activation='relu', padding='same'))
model.add(UpSampling2D((2, 2)))
model.add(Conv2D(64, (3, 3), activation='relu', padding='same'))
model.add(UpSampling2D((2, 2)))
model.add(Conv2D(32, (3, 3), activation='relu', padding='same'))
model.add(Conv2D(2, (3, 3), activation='tanh', padding='same'))
model.add(UpSampling2D((2, 2))) # Finish model
model.compile(optimizer='rmsprop', loss='mse')
self.model = model