]
decoder = Decoder(layers=layers,
num_channels=(NLAT + NEMB),
image_size=(1, 1),
weights_init=WEIGHTS_INIT,
biases_init=BIASES_INIT)
decoder.initialize()
decoder_fun = function([z, y], decoder.apply(z, embeddings))
out = decoder_fun(z_hat, test_labels)
# Discriminator
layers = [
conv_brick(5, 1, 32),
ConvMaxout(num_pieces=NUM_PIECES),
conv_brick(4, 2, 64),
ConvMaxout(num_pieces=NUM_PIECES),
conv_brick(4, 1, 128),
ConvMaxout(num_pieces=NUM_PIECES),
conv_brick(4, 2, 256),
ConvMaxout(num_pieces=NUM_PIECES),
conv_brick(4, 1, 512),
ConvMaxout(num_pieces=NUM_PIECES)
]
x_discriminator = ConvolutionalSequence(layers=layers,
num_channels=NUM_CHANNELS,
image_size=IMAGE_SIZE,
name='x_discriminator')
x_discriminator.push_allocation_config()
def create_model_brick():
layers = [
conv_brick(5, 1, 32),
bn_brick(),
LeakyRectifier(leak=LEAK),
conv_brick(4, 2, 64),
bn_brick(),
LeakyRectifier(leak=LEAK),
conv_brick(4, 1, 128),
bn_brick(),
LeakyRectifier(leak=LEAK),
conv_brick(4, 2, 256),
bn_brick(),
LeakyRectifier(leak=LEAK),
conv_brick(4, 1, 512),
bn_brick(),
LeakyRectifier(leak=LEAK),
conv_brick(1, 1, 512),
bn_brick(),
LeakyRectifier(leak=LEAK),
conv_brick(1, 1, 2 * NLAT)
]
encoder_mapping = ConvolutionalSequence(layers=layers,
num_channels=NUM_CHANNELS,
image_size=IMAGE_SIZE,
use_bias=False,
name='encoder_mapping')
encoder = GaussianConditional(encoder_mapping, name='encoder')
layers = [
conv_transpose_brick(4, 1, 256),
bn_brick(),
LeakyRectifier(leak=LEAK),
conv_transpose_brick(4, 2, 128),
bn_brick(),
LeakyRectifier(leak=LEAK),
conv_transpose_brick(4, 1, 64),
bn_brick(),
LeakyRectifier(leak=LEAK),
conv_transpose_brick(4, 2, 32),
bn_brick(),
LeakyRectifier(leak=LEAK),
conv_transpose_brick(5, 1, 32),
bn_brick(),
LeakyRectifier(leak=LEAK),
conv_transpose_brick(1, 1, 32),
bn_brick(),
LeakyRectifier(leak=LEAK),
conv_brick(1, 1, NUM_CHANNELS),
Logistic()
]
decoder_mapping = ConvolutionalSequence(layers=layers,
num_channels=NLAT,
image_size=(1, 1),
use_bias=False,
name='decoder_mapping')
decoder = DeterministicConditional(decoder_mapping, name='decoder')
layers = [
conv_brick(5, 1, 32),
ConvMaxout(num_pieces=NUM_PIECES),
conv_brick(4, 2, 64),
ConvMaxout(num_pieces=NUM_PIECES),
conv_brick(4, 1, 128),
ConvMaxout(num_pieces=NUM_PIECES),
conv_brick(4, 2, 256),
ConvMaxout(num_pieces=NUM_PIECES),
conv_brick(4, 1, 512),
ConvMaxout(num_pieces=NUM_PIECES)
]
x_discriminator = ConvolutionalSequence(layers=layers,
num_channels=NUM_CHANNELS,
image_size=IMAGE_SIZE,
name='x_discriminator')
x_discriminator.push_allocation_config()
layers = [
conv_brick(1, 1, 512),
ConvMaxout(num_pieces=NUM_PIECES),
conv_brick(1, 1, 512),
ConvMaxout(num_pieces=NUM_PIECES)
]
z_discriminator = ConvolutionalSequence(layers=layers,
num_channels=NLAT,
image_size=(1, 1),
use_bias=False,
name='z_discriminator')
z_discriminator.push_allocation_config()
layers = [
conv_brick(1, 1, 1024),
ConvMaxout(num_pieces=NUM_PIECES),
conv_brick(1, 1, 1024),
ConvMaxout(num_pieces=NUM_PIECES),
conv_brick(1, 1, 1)
]
joint_discriminator = ConvolutionalSequence(
layers=layers,
num_channels=(x_discriminator.get_dim('output')[0] +
z_discriminator.get_dim('output')[0]),
image_size=(1, 1),
name='joint_discriminator')
discriminator = XZJointDiscriminator(x_discriminator,
z_discriminator,
joint_discriminator,
name='discriminator')
ali = ALI(encoder,
decoder,
discriminator,
weights_init=GAUSSIAN_INIT,
biases_init=ZERO_INIT,
name='ali')
ali.push_allocation_config()
encoder_mapping.layers[-1].use_bias = True
encoder_mapping.layers[-1].tied_biases = False
decoder_mapping.layers[-2].use_bias = True
decoder_mapping.layers[-2].tied_biases = False
ali.initialize()
raw_marginals, = next(
create_cifar10_data_streams(500, 500)[0].get_epoch_iterator())
b_value = get_log_odds(raw_marginals)
decoder_mapping.layers[-2].b.set_value(b_value)
return ali