def generator(self, input):
if self.arch:
arch = self.arch
dim_z = arch['dim_z']
dim_c = arch['dim_c_G']
if arch['activation_G'] == 'relu':
activation_fn = tf.nn.relu
elif arch['activation_G'] == 'leakyRelu':
activation_fn = tf.nn.leaky_relu
else:
activation_fn = tf.nn.tanh
batchnorm = arch['batchnorm_G']
else:
dim_z = self.config.dim_z
dim_c = self.config.dim_c
activation_fn = tf.nn.relu
batchnorm = True
with tf.variable_scope('Generator'):
output = layers.linear(input, 4 * 4 * 4 * dim_c, name='LN1')
if batchnorm:
output = layers.batchnorm(output,
is_training=self.is_training,
name='BN1')
output = activation_fn(output)
output = tf.reshape(output, [-1, 4, 4, 4 * dim_c])
output_shape = [-1, 8, 8, 2 * dim_c]
output = layers.deconv2d(output, output_shape, name='Deconv2')
if batchnorm:
output = layers.batchnorm(output,
is_training=self.is_training,
name='BN2')
output = activation_fn(output)
output_shape = [-1, 16, 16, dim_c]
output = layers.deconv2d(output, output_shape, name='Decovn3')
if batchnorm:
output = layers.batchnorm(output,
is_training=self.is_training,
name='BN3')
output = activation_fn(output)
output_shape = [-1, 32, 32, 3]
output = layers.deconv2d(output, output_shape, name='Deconv4')
output = tf.nn.tanh(output)
return tf.reshape(output, [-1, 32 * 32 * 3])
def discriminator(self, inputs, reuse=False):
if self.arch:
arch = self.arch
dim_c = arch['dim_c_D']
if arch['activation_D'] == 'relu':
activation_fn = tf.nn.relu
elif arch['activation_D'] == 'leakyRelu':
activation_fn = tf.nn.leaky_relu
else:
activation_fn = tf.nn.tanh
batchnorm = arch['batchnorm_D']
else:
dim_c = self.config.dim_c
activation_fn = tf.nn.leaky_relu
batchnorm = False
with tf.variable_scope('Discriminator') as scope:
if reuse:
scope.reuse_variables()
output = tf.reshape(inputs, [-1, 28, 28, 1])
output = layers.conv2d(output, dim_c, name='Conv1')
output = activation_fn(output)
output = layers.conv2d(output, 2*dim_c, name='Conv2')
if batchnorm:
output = layers.batchnorm(output, is_training=self.is_training,
name='BN2')
output = activation_fn(output)
output = tf.reshape(output, [-1, 7*7*2*dim_c])
output = layers.linear(output, 1, name='LN3')
return tf.reshape(output, [-1])
def generator(self, input):
dim_x = self.config.dim_x
n_hidden = self.config.n_hidden_gen
with tf.variable_scope('Generator'):
output = layers.linear(input, n_hidden, name='LN1', stdev=0.2)
output = layers.batchnorm(output,
is_training=self.is_training,
name='BN1')
output = tf.nn.relu(output)
output = layers.linear(output, n_hidden, name='LN2', stdev=0.2)
output = layers.batchnorm(output,
is_training=self.is_training,
name='BN2')
output = tf.nn.relu(output)
output = layers.linear(output, dim_x, name='LN3', stdev=0.2)
#output = slim.fully_connected(input, n_hidden,
# activation_fn=tf.nn.relu)
#output = slim.fully_connected(output, n_hidden,
# activation_fn=tf.nn.relu)
#output = slim.fully_connected(output, dim_x, activation_fn=None)
return output
def _create_model(self, input_shape):
droprate = 0.20
enc_cfg, dec_cfg = configs[self.cfg_idx]
# ================== encoder ==================
with tf.name_scope('encoder_input'): # (N, M, 1)
encoder_input = Input(shape=input_shape, name="encoder_input")
with tf.name_scope('encoder_input_noise'): # (N, M, 1)
encoder = GaussianNoise(stddev=const.NOISE_STDDEV)(encoder_input)
with tf.name_scope('encoder_conv_1'): # (N/2, M/2, 32)
encoder = conv(enc_cfg[0], strides=2)(encoder)
encoder = batchnorm()(encoder)
encoder = dropout(droprate)(encoder)
with tf.name_scope('encoder_conv_2'): # (N/4, M/4, 32)
encoder = conv(enc_cfg[1], strides=2)(encoder)
encoder = batchnorm()(encoder)
encoder = dropout(droprate)(encoder)
with tf.name_scope('encoder_conv_3'): # (N/8, M/8, 32)
encoder = conv(enc_cfg[2], strides=2)(encoder)
encoder = batchnorm()(encoder)
encoder = dropout(droprate)(encoder)
if enc_cfg[3] > 0:
with tf.name_scope('encoder_conv_4'): # (N/10, M/10, 32)
encoder = conv(enc_cfg[3], strides=2)(encoder)
encoder = batchnorm()(encoder)
encoder = dropout(droprate)(encoder)
if enc_cfg[4] > 0:
with tf.name_scope('encoder_conv_4'): # (N/10, M/10, 32)
encoder = conv(enc_cfg[4], strides=2)(encoder)
encoder = batchnorm()(encoder)
encoder = dropout(droprate)(encoder)
with tf.name_scope('encoder_fully_connected_1'): # (512)
encoder = Flatten()(encoder)
encoder = dense(enc_cfg[5], activation=activations.lrelu)(encoder)
encoder = batchnorm()(encoder)
encoder = dropout(droprate)(encoder)
with tf.name_scope('encoder_fully_connected_2'): # (256)
encoder = dense(enc_cfg[6], activation=activations.relu)(encoder)
encoder_model = Model(inputs=encoder_input, outputs=encoder, name="encoder")
# ================== decoder ==================
with tf.name_scope('decoder_input'): # (N)
decoder_input = Input(shape=encoder_model.output_shape[1:], name="decoder_input")
# decoder_input = encoder
with tf.name_scope('decoder_fully_connected_1'): # (256)
decoder = dense(dec_cfg[0])(decoder_input)
with tf.name_scope('decoder_reshape_1'): # (2, 2, 64)
decoder = Reshape((2, 2, dec_cfg[0] // 4))(decoder)
with tf.name_scope('decoder_deconv_1'): # (4, 4, 32)
decoder = deconv(dec_cfg[1], strides=2)(decoder)
decoder = batchnorm()(decoder)
decoder = dropout(droprate)(decoder)
with tf.name_scope('decoder_deconv_2'): # (8, 8, 32)
decoder = deconv(dec_cfg[2], strides=2)(decoder)
decoder = batchnorm()(decoder)
decoder = dropout(droprate)(decoder)
with tf.name_scope('decoder_deconv_3'): # (16, 16, 32)
decoder = deconv(dec_cfg[3], strides=2)(decoder)
decoder = batchnorm()(decoder)
decoder = dropout(droprate)(decoder)
with tf.name_scope('decoder_deconv_4'): # (32, 32, 32)
decoder = deconv(dec_cfg[4], strides=2)(decoder)
decoder = batchnorm()(decoder)
decoder = dropout(droprate)(decoder)
with tf.name_scope('decoder_deconv_5'): # (64, 64, 3)
decoder = deconv(3, strides=2, activation=activations.relu)(decoder)
decoder_model = Model(inputs=decoder_input, outputs=decoder, name='decoder')
# ================== CAE ==================
model = Model(inputs=encoder_input, outputs=decoder_model(encoder_model(encoder_input)), name='cae')
self.encoder_model = encoder_model
self.decoder_model = decoder_model
return model
