def encode(self,
inputs,
target_space,
hparams,
features=None,
losses=None):
"""Add two layers strided convolutions ontop of encode."""
inputs = common_layers.conv_block(inputs,
hparams.hidden_size,
[((1, 1), (3, 3))],
first_relu=False,
padding="SAME",
force2d=True,
name="small_image_conv")
hparams.num_compress_steps = 2
compressed_inputs = transformer_vae.compress(inputs,
None,
is_2d=True,
hparams=hparams,
name="convolutions")
return super(TransformerSketch, self).encode(compressed_inputs,
target_space,
hparams,
features=features,
losses=losses)
def discriminator(x, compress, hparams, name, reuse=None):
with tf.variable_scope(name, reuse=reuse):
x = tf.stop_gradient(2 * x) - x # Reverse gradient.
if compress:
x = transformer_vae.compress(x, None, False, hparams, "compress")
else:
x = transformer_vae.residual_conv(x, 1, 3, hparams, "compress_rc")
y = tf.reduce_mean(x, axis=1)
return tf.tanh(tf.layers.dense(y, 1, name="reduce"))
def discriminator(x, compress, hparams, name, reuse=None):
with tf.variable_scope(name, reuse=reuse):
x = tf.stop_gradient(2 * x) - x # Reverse gradient.
if compress:
x = transformer_vae.compress(x, None, False, hparams, "compress")
else:
x = transformer_vae.residual_conv(x, 1, 3, hparams, "compress_rc")
y = tf.reduce_mean(x, axis=1)
return tf.tanh(tf.layers.dense(y, 1, name="reduce"))
def encode(self, inputs, target_space, hparams):
"""Add two layers strided convolutions ontop of encode."""
inputs = common_layers.conv_block(
inputs,
hparams.hidden_size, [((1, 1), (3, 3))],
first_relu=False,
padding="SAME",
force2d=True,
name="small_image_conv")
hparams.num_compress_steps = 2
compressed_inputs = transformer_vae.compress(inputs, is_2d=True,
hparams=hparams,
name="convolutions")
return super(TransformerSketch, self).encode(
compressed_inputs, target_space, hparams)
