def create_model_bricks():
convnet = ConvolutionalSequence(
layers=[
Convolutional(
filter_size=(4, 4),
num_filters=32,
name='conv1'),
SpatialBatchNormalization(name='batch_norm1'),
Rectifier(),
Convolutional(
filter_size=(3, 3),
step=(2, 2),
num_filters=32,
name='conv2'),
SpatialBatchNormalization(name='batch_norm2'),
Rectifier(),
Convolutional(
filter_size=(4, 4),
num_filters=64,
name='conv3'),
SpatialBatchNormalization(name='batch_norm3'),
Rectifier(),
Convolutional(
filter_size=(3, 3),
step=(2, 2),
num_filters=64,
name='conv4'),
SpatialBatchNormalization(name='batch_norm4'),
Rectifier(),
Convolutional(
filter_size=(3, 3),
num_filters=128,
name='conv5'),
SpatialBatchNormalization(name='batch_norm5'),
Rectifier(),
Convolutional(
filter_size=(3, 3),
step=(2, 2),
num_filters=128,
name='conv6'),
SpatialBatchNormalization(name='batch_norm6'),
Rectifier(),
],
num_channels=3,
image_size=(64, 64),
use_bias=False,
weights_init=IsotropicGaussian(0.033),
biases_init=Constant(0),
name='convnet')
convnet.initialize()
mlp = BatchNormalizedMLP(
activations=[Rectifier(), Logistic()],
dims=[numpy.prod(convnet.get_dim('output')), 1000, 40],
weights_init=IsotropicGaussian(0.033),
biases_init=Constant(0),
name='mlp')
mlp.initialize()
return convnet, mlp
def create_model_bricks(z_dim, image_size, depth):
g_image_size = image_size
g_image_size2 = g_image_size / 2
g_image_size3 = g_image_size / 4
g_image_size4 = g_image_size / 8
g_image_size5 = g_image_size / 16
encoder_layers = []
if depth > 0:
encoder_layers = encoder_layers + [
Convolutional(filter_size=(3, 3),
border_mode=(1, 1),
num_filters=32,
name='conv1'),
SpatialBatchNormalization(name='batch_norm1'),
Rectifier(),
Convolutional(filter_size=(3, 3),
border_mode=(1, 1),
num_filters=32,
name='conv2'),
SpatialBatchNormalization(name='batch_norm2'),
Rectifier(),
Convolutional(
filter_size=(2, 2), step=(2, 2), num_filters=32, name='conv3'),
SpatialBatchNormalization(name='batch_norm3'),
Rectifier()
]
if depth > 1:
encoder_layers = encoder_layers + [
Convolutional(filter_size=(3, 3),
border_mode=(1, 1),
num_filters=64,
name='conv4'),
SpatialBatchNormalization(name='batch_norm4'),
Rectifier(),
Convolutional(filter_size=(3, 3),
border_mode=(1, 1),
num_filters=64,
name='conv5'),
SpatialBatchNormalization(name='batch_norm5'),
Rectifier(),
Convolutional(
filter_size=(2, 2), step=(2, 2), num_filters=64, name='conv6'),
SpatialBatchNormalization(name='batch_norm6'),
Rectifier()
]
if depth > 2:
encoder_layers = encoder_layers + [
Convolutional(filter_size=(3, 3),
border_mode=(1, 1),
num_filters=128,
name='conv7'),
SpatialBatchNormalization(name='batch_norm7'),
Rectifier(),
Convolutional(filter_size=(3, 3),
border_mode=(1, 1),
num_filters=128,
name='conv8'),
SpatialBatchNormalization(name='batch_norm8'),
Rectifier(),
Convolutional(
filter_size=(2, 2), step=(2, 2), num_filters=128,
name='conv9'),
SpatialBatchNormalization(name='batch_norm9'),
Rectifier()
]
if depth > 3:
encoder_layers = encoder_layers + [
Convolutional(filter_size=(3, 3),
border_mode=(1, 1),
num_filters=256,
name='conv10'),
SpatialBatchNormalization(name='batch_norm10'),
Rectifier(),
Convolutional(filter_size=(3, 3),
border_mode=(1, 1),
num_filters=256,
name='conv11'),
SpatialBatchNormalization(name='batch_norm11'),
Rectifier(),
Convolutional(filter_size=(2, 2),
step=(2, 2),
num_filters=256,
name='conv12'),
SpatialBatchNormalization(name='batch_norm12'),
Rectifier(),
]
if depth > 4:
encoder_layers = encoder_layers + [
Convolutional(filter_size=(3, 3),
border_mode=(1, 1),
num_filters=512,
name='conv13'),
SpatialBatchNormalization(name='batch_norm13'),
Rectifier(),
Convolutional(filter_size=(3, 3),
border_mode=(1, 1),
num_filters=512,
name='conv14'),
SpatialBatchNormalization(name='batch_norm14'),
Rectifier(),
Convolutional(filter_size=(2, 2),
step=(2, 2),
num_filters=512,
name='conv15'),
SpatialBatchNormalization(name='batch_norm15'),
Rectifier()
]
decoder_layers = []
if depth > 4:
decoder_layers = decoder_layers + [
Convolutional(filter_size=(3, 3),
border_mode=(1, 1),
num_filters=512,
name='conv_n3'),
SpatialBatchNormalization(name='batch_norm_n3'),
Rectifier(),
Convolutional(filter_size=(3, 3),
border_mode=(1, 1),
num_filters=512,
name='conv_n2'),
SpatialBatchNormalization(name='batch_norm_n2'),
Rectifier(),
ConvolutionalTranspose(
filter_size=(2, 2),
step=(2, 2),
original_image_size=(g_image_size5, g_image_size5),
num_filters=512,
name='conv_n1'),
SpatialBatchNormalization(name='batch_norm_n1'),
Rectifier()
]
if depth > 3:
decoder_layers = decoder_layers + [
Convolutional(filter_size=(3, 3),
border_mode=(1, 1),
num_filters=256,
name='conv1'),
SpatialBatchNormalization(name='batch_norm1'),
Rectifier(),
Convolutional(filter_size=(3, 3),
border_mode=(1, 1),
num_filters=256,
name='conv2'),
SpatialBatchNormalization(name='batch_norm2'),
Rectifier(),
ConvolutionalTranspose(
filter_size=(2, 2),
step=(2, 2),
original_image_size=(g_image_size4, g_image_size4),
num_filters=256,
name='conv3'),
SpatialBatchNormalization(name='batch_norm3'),
Rectifier()
]
if depth > 2:
decoder_layers = decoder_layers + [
Convolutional(filter_size=(3, 3),
border_mode=(1, 1),
num_filters=128,
name='conv4'),
SpatialBatchNormalization(name='batch_norm4'),
Rectifier(),
Convolutional(filter_size=(3, 3),
border_mode=(1, 1),
num_filters=128,
name='conv5'),
SpatialBatchNormalization(name='batch_norm5'),
Rectifier(),
ConvolutionalTranspose(
filter_size=(2, 2),
step=(2, 2),
original_image_size=(g_image_size3, g_image_size3),
num_filters=128,
name='conv6'),
SpatialBatchNormalization(name='batch_norm6'),
Rectifier()
]
if depth > 1:
decoder_layers = decoder_layers + [
Convolutional(filter_size=(3, 3),
border_mode=(1, 1),
num_filters=64,
name='conv7'),
SpatialBatchNormalization(name='batch_norm7'),
Rectifier(),
Convolutional(filter_size=(3, 3),
border_mode=(1, 1),
num_filters=64,
name='conv8'),
SpatialBatchNormalization(name='batch_norm8'),
Rectifier(),
ConvolutionalTranspose(
filter_size=(2, 2),
step=(2, 2),
original_image_size=(g_image_size2, g_image_size2),
num_filters=64,
name='conv9'),
SpatialBatchNormalization(name='batch_norm9'),
Rectifier()
]
if depth > 0:
decoder_layers = decoder_layers + [
Convolutional(filter_size=(3, 3),
border_mode=(1, 1),
num_filters=32,
name='conv10'),
SpatialBatchNormalization(name='batch_norm10'),
Rectifier(),
Convolutional(filter_size=(3, 3),
border_mode=(1, 1),
num_filters=32,
name='conv11'),
SpatialBatchNormalization(name='batch_norm11'),
Rectifier(),
ConvolutionalTranspose(
filter_size=(2, 2),
step=(2, 2),
original_image_size=(g_image_size, g_image_size),
num_filters=32,
name='conv12'),
SpatialBatchNormalization(name='batch_norm12'),
Rectifier()
]
decoder_layers = decoder_layers + [
Convolutional(filter_size=(1, 1), num_filters=3, name='conv_out'),
Logistic()
]
print("creating model of depth {} with {} encoder and {} decoder layers".
format(depth, len(encoder_layers), len(decoder_layers)))
encoder_convnet = ConvolutionalSequence(
layers=encoder_layers,
num_channels=3,
image_size=(g_image_size, g_image_size),
use_bias=False,
weights_init=IsotropicGaussian(0.033),
biases_init=Constant(0),
name='encoder_convnet')
encoder_convnet.initialize()
encoder_filters = numpy.prod(encoder_convnet.get_dim('output'))
encoder_mlp = MLP(
dims=[encoder_filters, 1000, z_dim],
activations=[
Sequence([BatchNormalization(1000).apply,
Rectifier().apply],
name='activation1'),
Identity().apply
],
weights_init=IsotropicGaussian(0.033),
biases_init=Constant(0),
name='encoder_mlp')
encoder_mlp.initialize()
decoder_mlp = BatchNormalizedMLP(
activations=[Rectifier(), Rectifier()],
dims=[encoder_mlp.output_dim // 2, 1000, encoder_filters],
weights_init=IsotropicGaussian(0.033),
biases_init=Constant(0),
name='decoder_mlp')
decoder_mlp.initialize()
decoder_convnet = ConvolutionalSequence(
layers=decoder_layers,
num_channels=encoder_convnet.get_dim('output')[0],
image_size=encoder_convnet.get_dim('output')[1:],
use_bias=False,
weights_init=IsotropicGaussian(0.033),
biases_init=Constant(0),
name='decoder_convnet')
decoder_convnet.initialize()
return encoder_convnet, encoder_mlp, decoder_convnet, decoder_mlp
def create_model_bricks():
encoder_convnet = ConvolutionalSequence(
layers=[
Convolutional(
filter_size=(3, 3),
border_mode=(1, 1),
num_filters=32,
name='conv1'),
SpatialBatchNormalization(name='batch_norm1'),
Rectifier(),
Convolutional(
filter_size=(3, 3),
border_mode=(1, 1),
num_filters=32,
name='conv2'),
SpatialBatchNormalization(name='batch_norm2'),
Rectifier(),
Convolutional(
filter_size=(2, 2),
step=(2, 2),
num_filters=32,
name='conv3'),
SpatialBatchNormalization(name='batch_norm3'),
Rectifier(),
Convolutional(
filter_size=(3, 3),
border_mode=(1, 1),
num_filters=64,
name='conv4'),
SpatialBatchNormalization(name='batch_norm4'),
Rectifier(),
Convolutional(
filter_size=(3, 3),
border_mode=(1, 1),
num_filters=64,
name='conv5'),
SpatialBatchNormalization(name='batch_norm5'),
Rectifier(),
Convolutional(
filter_size=(2, 2),
step=(2, 2),
num_filters=64,
name='conv6'),
SpatialBatchNormalization(name='batch_norm6'),
Rectifier(),
Convolutional(
filter_size=(3, 3),
border_mode=(1, 1),
num_filters=128,
name='conv7'),
SpatialBatchNormalization(name='batch_norm7'),
Rectifier(),
Convolutional(
filter_size=(3, 3),
border_mode=(1, 1),
num_filters=128,
name='conv8'),
SpatialBatchNormalization(name='batch_norm8'),
Rectifier(),
Convolutional(
filter_size=(2, 2),
step=(2, 2),
num_filters=128,
name='conv9'),
SpatialBatchNormalization(name='batch_norm9'),
Rectifier(),
Convolutional(
filter_size=(3, 3),
border_mode=(1, 1),
num_filters=256,
name='conv10'),
SpatialBatchNormalization(name='batch_norm10'),
Rectifier(),
Convolutional(
filter_size=(3, 3),
border_mode=(1, 1),
num_filters=256,
name='conv11'),
SpatialBatchNormalization(name='batch_norm11'),
Rectifier(),
Convolutional(
filter_size=(2, 2),
step=(2, 2),
num_filters=256,
name='conv12'),
SpatialBatchNormalization(name='batch_norm12'),
Rectifier(),
],
num_channels=3,
image_size=(64, 64),
use_bias=False,
weights_init=IsotropicGaussian(0.033),
biases_init=Constant(0),
name='encoder_convnet')
encoder_convnet.initialize()
encoder_filters = numpy.prod(encoder_convnet.get_dim('output'))
encoder_mlp = MLP(
dims=[encoder_filters, 1000, 1000],
activations=[Sequence([BatchNormalization(1000).apply,
Rectifier().apply], name='activation1'),
Identity().apply],
weights_init=IsotropicGaussian(0.033),
biases_init=Constant(0),
name='encoder_mlp')
encoder_mlp.initialize()
decoder_mlp = BatchNormalizedMLP(
activations=[Rectifier(), Rectifier()],
dims=[encoder_mlp.output_dim // 2, 1000, encoder_filters],
weights_init=IsotropicGaussian(0.033),
biases_init=Constant(0),
name='decoder_mlp')
decoder_mlp.initialize()
decoder_convnet = ConvolutionalSequence(
layers=[
Convolutional(
filter_size=(3, 3),
border_mode=(1, 1),
num_filters=256,
name='conv1'),
SpatialBatchNormalization(name='batch_norm1'),
Rectifier(),
Convolutional(
filter_size=(3, 3),
border_mode=(1, 1),
num_filters=256,
name='conv2'),
SpatialBatchNormalization(name='batch_norm2'),
Rectifier(),
ConvolutionalTranspose(
filter_size=(2, 2),
step=(2, 2),
original_image_size=(8, 8),
num_filters=256,
name='conv3'),
SpatialBatchNormalization(name='batch_norm3'),
Rectifier(),
Convolutional(
filter_size=(3, 3),
border_mode=(1, 1),
num_filters=128,
name='conv4'),
SpatialBatchNormalization(name='batch_norm4'),
Rectifier(),
Convolutional(
filter_size=(3, 3),
border_mode=(1, 1),
num_filters=128,
name='conv5'),
SpatialBatchNormalization(name='batch_norm5'),
Rectifier(),
ConvolutionalTranspose(
filter_size=(2, 2),
step=(2, 2),
original_image_size=(16, 16),
num_filters=128,
name='conv6'),
SpatialBatchNormalization(name='batch_norm6'),
Rectifier(),
Convolutional(
filter_size=(3, 3),
border_mode=(1, 1),
num_filters=64,
name='conv7'),
SpatialBatchNormalization(name='batch_norm7'),
Rectifier(),
Convolutional(
filter_size=(3, 3),
border_mode=(1, 1),
num_filters=64,
name='conv8'),
SpatialBatchNormalization(name='batch_norm8'),
Rectifier(),
ConvolutionalTranspose(
filter_size=(2, 2),
step=(2, 2),
original_image_size=(32, 32),
num_filters=64,
name='conv9'),
SpatialBatchNormalization(name='batch_norm9'),
Rectifier(),
Convolutional(
filter_size=(3, 3),
border_mode=(1, 1),
num_filters=32,
name='conv10'),
SpatialBatchNormalization(name='batch_norm10'),
Rectifier(),
Convolutional(
filter_size=(3, 3),
border_mode=(1, 1),
num_filters=32,
name='conv11'),
SpatialBatchNormalization(name='batch_norm11'),
Rectifier(),
ConvolutionalTranspose(
filter_size=(2, 2),
step=(2, 2),
original_image_size=(64, 64),
num_filters=32,
name='conv12'),
SpatialBatchNormalization(name='batch_norm12'),
Rectifier(),
Convolutional(
filter_size=(1, 1),
num_filters=3,
name='conv_out'),
Logistic(),
],
num_channels=encoder_convnet.get_dim('output')[0],
image_size=encoder_convnet.get_dim('output')[1:],
use_bias=False,
weights_init=IsotropicGaussian(0.033),
biases_init=Constant(0),
name='decoder_convnet')
decoder_convnet.initialize()
return encoder_convnet, encoder_mlp, decoder_convnet, decoder_mlp
def create_model_bricks(z_dim, image_size, depth):
g_image_size = image_size
g_image_size2 = g_image_size / 2
g_image_size3 = g_image_size / 4
g_image_size4 = g_image_size / 8
g_image_size5 = g_image_size / 16
encoder_layers = []
if depth > 0:
encoder_layers = encoder_layers + [
Convolutional(filter_size=(3, 3), border_mode=(1, 1), num_filters=32, name="conv1"),
SpatialBatchNormalization(name="batch_norm1"),
Rectifier(),
Convolutional(filter_size=(3, 3), border_mode=(1, 1), num_filters=32, name="conv2"),
SpatialBatchNormalization(name="batch_norm2"),
Rectifier(),
Convolutional(filter_size=(2, 2), step=(2, 2), num_filters=32, name="conv3"),
SpatialBatchNormalization(name="batch_norm3"),
Rectifier(),
]
if depth > 1:
encoder_layers = encoder_layers + [
Convolutional(filter_size=(3, 3), border_mode=(1, 1), num_filters=64, name="conv4"),
SpatialBatchNormalization(name="batch_norm4"),
Rectifier(),
Convolutional(filter_size=(3, 3), border_mode=(1, 1), num_filters=64, name="conv5"),
SpatialBatchNormalization(name="batch_norm5"),
Rectifier(),
Convolutional(filter_size=(2, 2), step=(2, 2), num_filters=64, name="conv6"),
SpatialBatchNormalization(name="batch_norm6"),
Rectifier(),
]
if depth > 2:
encoder_layers = encoder_layers + [
Convolutional(filter_size=(3, 3), border_mode=(1, 1), num_filters=128, name="conv7"),
SpatialBatchNormalization(name="batch_norm7"),
Rectifier(),
Convolutional(filter_size=(3, 3), border_mode=(1, 1), num_filters=128, name="conv8"),
SpatialBatchNormalization(name="batch_norm8"),
Rectifier(),
Convolutional(filter_size=(2, 2), step=(2, 2), num_filters=128, name="conv9"),
SpatialBatchNormalization(name="batch_norm9"),
Rectifier(),
]
if depth > 3:
encoder_layers = encoder_layers + [
Convolutional(filter_size=(3, 3), border_mode=(1, 1), num_filters=256, name="conv10"),
SpatialBatchNormalization(name="batch_norm10"),
Rectifier(),
Convolutional(filter_size=(3, 3), border_mode=(1, 1), num_filters=256, name="conv11"),
SpatialBatchNormalization(name="batch_norm11"),
Rectifier(),
Convolutional(filter_size=(2, 2), step=(2, 2), num_filters=256, name="conv12"),
SpatialBatchNormalization(name="batch_norm12"),
Rectifier(),
]
if depth > 4:
encoder_layers = encoder_layers + [
Convolutional(filter_size=(3, 3), border_mode=(1, 1), num_filters=512, name="conv13"),
SpatialBatchNormalization(name="batch_norm13"),
Rectifier(),
Convolutional(filter_size=(3, 3), border_mode=(1, 1), num_filters=512, name="conv14"),
SpatialBatchNormalization(name="batch_norm14"),
Rectifier(),
Convolutional(filter_size=(2, 2), step=(2, 2), num_filters=512, name="conv15"),
SpatialBatchNormalization(name="batch_norm15"),
Rectifier(),
]
decoder_layers = []
if depth > 4:
decoder_layers = decoder_layers + [
Convolutional(filter_size=(3, 3), border_mode=(1, 1), num_filters=512, name="conv_n3"),
SpatialBatchNormalization(name="batch_norm_n3"),
Rectifier(),
Convolutional(filter_size=(3, 3), border_mode=(1, 1), num_filters=512, name="conv_n2"),
SpatialBatchNormalization(name="batch_norm_n2"),
Rectifier(),
ConvolutionalTranspose(
filter_size=(2, 2),
step=(2, 2),
original_image_size=(g_image_size5, g_image_size5),
num_filters=512,
name="conv_n1",
),
SpatialBatchNormalization(name="batch_norm_n1"),
Rectifier(),
]
if depth > 3:
decoder_layers = decoder_layers + [
Convolutional(filter_size=(3, 3), border_mode=(1, 1), num_filters=256, name="conv1"),
SpatialBatchNormalization(name="batch_norm1"),
Rectifier(),
Convolutional(filter_size=(3, 3), border_mode=(1, 1), num_filters=256, name="conv2"),
SpatialBatchNormalization(name="batch_norm2"),
Rectifier(),
ConvolutionalTranspose(
filter_size=(2, 2),
step=(2, 2),
original_image_size=(g_image_size4, g_image_size4),
num_filters=256,
name="conv3",
),
SpatialBatchNormalization(name="batch_norm3"),
Rectifier(),
]
if depth > 2:
decoder_layers = decoder_layers + [
Convolutional(filter_size=(3, 3), border_mode=(1, 1), num_filters=128, name="conv4"),
SpatialBatchNormalization(name="batch_norm4"),
Rectifier(),
Convolutional(filter_size=(3, 3), border_mode=(1, 1), num_filters=128, name="conv5"),
SpatialBatchNormalization(name="batch_norm5"),
Rectifier(),
ConvolutionalTranspose(
filter_size=(2, 2),
step=(2, 2),
original_image_size=(g_image_size3, g_image_size3),
num_filters=128,
name="conv6",
),
SpatialBatchNormalization(name="batch_norm6"),
Rectifier(),
]
if depth > 1:
decoder_layers = decoder_layers + [
Convolutional(filter_size=(3, 3), border_mode=(1, 1), num_filters=64, name="conv7"),
SpatialBatchNormalization(name="batch_norm7"),
Rectifier(),
Convolutional(filter_size=(3, 3), border_mode=(1, 1), num_filters=64, name="conv8"),
SpatialBatchNormalization(name="batch_norm8"),
Rectifier(),
ConvolutionalTranspose(
filter_size=(2, 2),
step=(2, 2),
original_image_size=(g_image_size2, g_image_size2),
num_filters=64,
name="conv9",
),
SpatialBatchNormalization(name="batch_norm9"),
Rectifier(),
]
if depth > 0:
decoder_layers = decoder_layers + [
Convolutional(filter_size=(3, 3), border_mode=(1, 1), num_filters=32, name="conv10"),
SpatialBatchNormalization(name="batch_norm10"),
Rectifier(),
Convolutional(filter_size=(3, 3), border_mode=(1, 1), num_filters=32, name="conv11"),
SpatialBatchNormalization(name="batch_norm11"),
Rectifier(),
ConvolutionalTranspose(
filter_size=(2, 2),
step=(2, 2),
original_image_size=(g_image_size, g_image_size),
num_filters=32,
name="conv12",
),
SpatialBatchNormalization(name="batch_norm12"),
Rectifier(),
]
decoder_layers = decoder_layers + [Convolutional(filter_size=(1, 1), num_filters=3, name="conv_out"), Logistic()]
print(
"creating model of depth {} with {} encoder and {} decoder layers".format(
depth, len(encoder_layers), len(decoder_layers)
)
)
encoder_convnet = ConvolutionalSequence(
layers=encoder_layers,
num_channels=3,
image_size=(g_image_size, g_image_size),
use_bias=False,
weights_init=IsotropicGaussian(0.033),
biases_init=Constant(0),
name="encoder_convnet",
)
encoder_convnet.initialize()
encoder_filters = numpy.prod(encoder_convnet.get_dim("output"))
encoder_mlp = MLP(
dims=[encoder_filters, 1000, z_dim],
activations=[
Sequence([BatchNormalization(1000).apply, Rectifier().apply], name="activation1"),
Identity().apply,
],
weights_init=IsotropicGaussian(0.033),
biases_init=Constant(0),
name="encoder_mlp",
)
encoder_mlp.initialize()
decoder_mlp = BatchNormalizedMLP(
activations=[Rectifier(), Rectifier()],
dims=[encoder_mlp.output_dim // 2, 1000, encoder_filters],
weights_init=IsotropicGaussian(0.033),
biases_init=Constant(0),
name="decoder_mlp",
)
decoder_mlp.initialize()
decoder_convnet = ConvolutionalSequence(
layers=decoder_layers,
num_channels=encoder_convnet.get_dim("output")[0],
image_size=encoder_convnet.get_dim("output")[1:],
use_bias=False,
weights_init=IsotropicGaussian(0.033),
biases_init=Constant(0),
name="decoder_convnet",
)
decoder_convnet.initialize()
return encoder_convnet, encoder_mlp, decoder_convnet, decoder_mlp
def create_model_bricks():
encoder_convnet = ConvolutionalSequence(
layers=[
Convolutional(filter_size=(3, 3),
border_mode=(1, 1),
num_filters=32,
name='conv1'),
SpatialBatchNormalization(name='batch_norm1'),
Rectifier(),
Convolutional(filter_size=(3, 3),
border_mode=(1, 1),
num_filters=32,
name='conv2'),
SpatialBatchNormalization(name='batch_norm2'),
Rectifier(),
Convolutional(filter_size=(2, 2),
step=(2, 2),
num_filters=32,
name='conv3'),
SpatialBatchNormalization(name='batch_norm3'),
Rectifier(),
Convolutional(filter_size=(3, 3),
border_mode=(1, 1),
num_filters=64,
name='conv4'),
SpatialBatchNormalization(name='batch_norm4'),
Rectifier(),
Convolutional(filter_size=(3, 3),
border_mode=(1, 1),
num_filters=64,
name='conv5'),
SpatialBatchNormalization(name='batch_norm5'),
Rectifier(),
Convolutional(filter_size=(2, 2),
step=(2, 2),
num_filters=64,
name='conv6'),
SpatialBatchNormalization(name='batch_norm6'),
Rectifier(),
Convolutional(filter_size=(3, 3),
border_mode=(1, 1),
num_filters=128,
name='conv7'),
SpatialBatchNormalization(name='batch_norm7'),
Rectifier(),
Convolutional(filter_size=(3, 3),
border_mode=(1, 1),
num_filters=128,
name='conv8'),
SpatialBatchNormalization(name='batch_norm8'),
Rectifier(),
Convolutional(filter_size=(2, 2),
step=(2, 2),
num_filters=128,
name='conv9'),
SpatialBatchNormalization(name='batch_norm9'),
Rectifier(),
Convolutional(filter_size=(3, 3),
border_mode=(1, 1),
num_filters=256,
name='conv10'),
SpatialBatchNormalization(name='batch_norm10'),
Rectifier(),
Convolutional(filter_size=(3, 3),
border_mode=(1, 1),
num_filters=256,
name='conv11'),
SpatialBatchNormalization(name='batch_norm11'),
Rectifier(),
Convolutional(filter_size=(2, 2),
step=(2, 2),
num_filters=256,
name='conv12'),
SpatialBatchNormalization(name='batch_norm12'),
Rectifier(),
],
num_channels=3,
image_size=(64, 64),
use_bias=False,
weights_init=IsotropicGaussian(0.033),
biases_init=Constant(0),
name='encoder_convnet')
encoder_convnet.initialize()
encoder_filters = numpy.prod(encoder_convnet.get_dim('output'))
encoder_mlp = MLP(
dims=[encoder_filters, 1000, 1000],
activations=[
Sequence([BatchNormalization(1000).apply,
Rectifier().apply],
name='activation1'),
Identity().apply
],
weights_init=IsotropicGaussian(0.033),
biases_init=Constant(0),
name='encoder_mlp')
encoder_mlp.initialize()
decoder_mlp = BatchNormalizedMLP(
activations=[Rectifier(), Rectifier()],
dims=[encoder_mlp.output_dim // 2, 1000, encoder_filters],
weights_init=IsotropicGaussian(0.033),
biases_init=Constant(0),
name='decoder_mlp')
decoder_mlp.initialize()
decoder_convnet = ConvolutionalSequence(
layers=[
Convolutional(filter_size=(3, 3),
border_mode=(1, 1),
num_filters=256,
name='conv1'),
SpatialBatchNormalization(name='batch_norm1'),
Rectifier(),
Convolutional(filter_size=(3, 3),
border_mode=(1, 1),
num_filters=256,
name='conv2'),
SpatialBatchNormalization(name='batch_norm2'),
Rectifier(),
ConvolutionalTranspose(filter_size=(2, 2),
step=(2, 2),
original_image_size=(8, 8),
num_filters=256,
name='conv3'),
SpatialBatchNormalization(name='batch_norm3'),
Rectifier(),
Convolutional(filter_size=(3, 3),
border_mode=(1, 1),
num_filters=128,
name='conv4'),
SpatialBatchNormalization(name='batch_norm4'),
Rectifier(),
Convolutional(filter_size=(3, 3),
border_mode=(1, 1),
num_filters=128,
name='conv5'),
SpatialBatchNormalization(name='batch_norm5'),
Rectifier(),
ConvolutionalTranspose(filter_size=(2, 2),
step=(2, 2),
original_image_size=(16, 16),
num_filters=128,
name='conv6'),
SpatialBatchNormalization(name='batch_norm6'),
Rectifier(),
Convolutional(filter_size=(3, 3),
border_mode=(1, 1),
num_filters=64,
name='conv7'),
SpatialBatchNormalization(name='batch_norm7'),
Rectifier(),
Convolutional(filter_size=(3, 3),
border_mode=(1, 1),
num_filters=64,
name='conv8'),
SpatialBatchNormalization(name='batch_norm8'),
Rectifier(),
ConvolutionalTranspose(filter_size=(2, 2),
step=(2, 2),
original_image_size=(32, 32),
num_filters=64,
name='conv9'),
SpatialBatchNormalization(name='batch_norm9'),
Rectifier(),
Convolutional(filter_size=(3, 3),
border_mode=(1, 1),
num_filters=32,
name='conv10'),
SpatialBatchNormalization(name='batch_norm10'),
Rectifier(),
Convolutional(filter_size=(3, 3),
border_mode=(1, 1),
num_filters=32,
name='conv11'),
SpatialBatchNormalization(name='batch_norm11'),
Rectifier(),
ConvolutionalTranspose(filter_size=(2, 2),
step=(2, 2),
original_image_size=(64, 64),
num_filters=32,
name='conv12'),
SpatialBatchNormalization(name='batch_norm12'),
Rectifier(),
Convolutional(filter_size=(1, 1), num_filters=3, name='conv_out'),
Logistic(),
],
num_channels=encoder_convnet.get_dim('output')[0],
image_size=encoder_convnet.get_dim('output')[1:],
use_bias=False,
weights_init=IsotropicGaussian(0.033),
biases_init=Constant(0),
name='decoder_convnet')
decoder_convnet.initialize()
return encoder_convnet, encoder_mlp, decoder_convnet, decoder_mlp
def create_model_bricks(image_size, depth):
# original celebA64 was depth=3 (went to bach_norm6)
layers = []
if(depth > 0):
layers = layers + [
Convolutional(
filter_size=(4, 4),
num_filters=32,
name='conv1'),
SpatialBatchNormalization(name='batch_norm1'),
Rectifier(),
Convolutional(
filter_size=(3, 3),
step=(2, 2),
num_filters=32,
name='conv2'),
SpatialBatchNormalization(name='batch_norm2'),
Rectifier(),
]
if(depth > 1):
layers = layers + [
Convolutional(
filter_size=(4, 4),
num_filters=64,
name='conv3'),
SpatialBatchNormalization(name='batch_norm3'),
Rectifier(),
Convolutional(
filter_size=(3, 3),
step=(2, 2),
num_filters=64,
name='conv4'),
SpatialBatchNormalization(name='batch_norm4'),
Rectifier(),
]
if(depth > 2):
layers = layers + [
Convolutional(
filter_size=(3, 3),
num_filters=128,
name='conv5'),
SpatialBatchNormalization(name='batch_norm5'),
Rectifier(),
Convolutional(
filter_size=(3, 3),
step=(2, 2),
num_filters=128,
name='conv6'),
SpatialBatchNormalization(name='batch_norm6'),
Rectifier(),
]
if(depth > 3):
layers = layers + [
Convolutional(
filter_size=(3, 3),
num_filters=256,
name='conv7'),
SpatialBatchNormalization(name='batch_norm7'),
Rectifier(),
Convolutional(
filter_size=(3, 3),
step=(2, 2),
num_filters=256,
name='conv8'),
SpatialBatchNormalization(name='batch_norm8'),
Rectifier(),
]
if(depth > 4):
layers = layers + [
Convolutional(
filter_size=(3, 3),
num_filters=512,
name='conv9'),
SpatialBatchNormalization(name='batch_norm9'),
Rectifier(),
Convolutional(
filter_size=(3, 3),
step=(2, 2),
num_filters=512,
name='conv10'),
SpatialBatchNormalization(name='batch_norm10'),
Rectifier(),
]
if(depth > 5):
layers = layers + [
Convolutional(
filter_size=(3, 3),
num_filters=512,
name='conv11'),
SpatialBatchNormalization(name='batch_norm11'),
Rectifier(),
Convolutional(
filter_size=(3, 3),
step=(2, 2),
num_filters=512,
name='conv12'),
SpatialBatchNormalization(name='batch_norm12'),
Rectifier(),
]
if(depth > 6):
layers = layers + [
Convolutional(
filter_size=(3, 3),
num_filters=512,
name='conv13'),
SpatialBatchNormalization(name='batch_norm13'),
Rectifier(),
Convolutional(
filter_size=(3, 3),
step=(2, 2),
num_filters=512,
name='conv14'),
SpatialBatchNormalization(name='batch_norm14'),
Rectifier(),
]
if(depth > 7):
layers = layers + [
Convolutional(
filter_size=(3, 3),
num_filters=512,
name='conv15'),
SpatialBatchNormalization(name='batch_norm15'),
Rectifier(),
Convolutional(
filter_size=(3, 3),
step=(2, 2),
num_filters=512,
name='conv16'),
SpatialBatchNormalization(name='batch_norm16'),
Rectifier(),
]
print("creating model of depth {} with {} layers".format(depth, len(layers)))
convnet = ConvolutionalSequence(
layers=layers,
num_channels=3,
image_size=(image_size, image_size),
use_bias=False,
weights_init=IsotropicGaussian(0.033),
biases_init=Constant(0),
name='convnet')
convnet.initialize()
mlp = BatchNormalizedMLP(
activations=[Rectifier(), Logistic()],
dims=[numpy.prod(convnet.get_dim('output')), 1000, 64],
weights_init=IsotropicGaussian(0.033),
biases_init=Constant(0),
name='mlp')
mlp.initialize()
return convnet, mlp, len(layers)