def cin_resnet_block(input_shape, z_dim, padding, norm_layer, use_dropout,
use_bias, block_name, **kwargs):
num_filters = input_shape[1]
block = nn.Sequential(input_shape=input_shape, layer_name=block_name)
block.append(
nn.Conv2DLayer(input_shape,
num_filters,
3,
border_mode=padding,
no_bias=not use_bias,
activation=None,
layer_name=block_name + '/conv1'))
block.append(norm_layer(input_shape, z_dim,
layer_name=block_name + '/CIN'))
block.append(
nn.ActivationLayer(block.output_shape,
layer_name=block_name + '/relu1'))
if use_dropout:
block.append(
nn.DropoutLayer(block.output_shape,
.5,
layer_name=block_name + '/dropout'))
block.append(
nn.Conv2DLayer(block.output_shape,
num_filters,
3,
border_mode=padding,
no_bias=not use_bias,
activation=None,
layer_name=block_name + '/conv2'))
block.append(nn.InstanceNormLayer(block.output_shape, block_name + '/IN'))
return block
def __init__(self, config_file, **kwargs):
super(DeepLTE, self).__init__(config_file, **kwargs)
self.num_frames = self.config['model']['num_frames']
self.order = self.config['model']['order']
self.nodes = self.config['model']['nodes']
self.targets = self.config['model']['targets']
self.interps = self.config['model']['interps']
self.alpha = self.config['model']['alpha']
self.dropout = self.config['model']['dropout']
self.perceptual_cost = self.config['model']['perceptual_cost']
self.vgg_weight_file = self.config['model']['vgg_weight_file']
self.input_tensor_shape = (None,) + self.input_shape[1:]
enc = nn.model_zoo.resnet34(self.input_tensor_shape, 64, 'lrelu', False, False, name='encoder', alpha=self.alpha)
self.model.append(enc)
subnet = 'decoder'
dec = nn.Sequential(input_shape=enc.output_shape, layer_name='decoder')
dec.append(nn.ResizingLayer(dec.input_shape, 2, layer_name=subnet + '_up1'))
dec.append(nn.StackingConv(dec.output_shape, 3, 256, 5, batch_norm=False, layer_name=subnet + '_block5',
He_init='normal', stride=(1, 1), activation='lrelu', alpha=self.alpha))
dec.append(nn.ResizingLayer(dec.output_shape, 2, layer_name=subnet + '_up2'))
dec.append(nn.StackingConv(dec.output_shape, 5, 128, 5, batch_norm=False, layer_name=subnet + '_block6',
He_init='normal', stride=(1, 1), activation='lrelu', alpha=self.alpha))
dec.append(nn.ResizingLayer(dec.output_shape, 2, layer_name=subnet + '_up3'))
dec.append(nn.StackingConv(dec.output_shape, 6, 128, 5, batch_norm=False, layer_name=subnet + '_block7',
He_init='normal', stride=(1, 1), activation='lrelu', alpha=self.alpha))
dec.append(nn.ConvolutionalLayer(dec.output_shape, 128, 5, activation='linear', layer_name=subnet+'_conv7'))
if self.dropout:
dec.append(nn.DropoutLayer(dec.output_shape, drop_prob=.5, layer_name=subnet + '_dropout7'))
dec.append(nn.ActivationLayer(dec.output_shape, 'lrelu', subnet+'_act7', alpha=self.alpha))
dec.append(nn.ResizingLayer(dec.output_shape, 2, layer_name=subnet + '_up4'))
dec.append(nn.StackingConv(dec.output_shape, 8, 64, 5, batch_norm=False, layer_name=subnet + '_block8',
He_init='normal', stride=(1, 1), activation='lrelu', alpha=self.alpha))
dec.append(nn.ConvolutionalLayer(dec.output_shape, 64, 5, activation='linear', layer_name=subnet + '_conv8'))
if self.dropout:
dec.append(nn.DropoutLayer(dec.output_shape, drop_prob=.5, layer_name=subnet + '_dropout8'))
dec.append(nn.ActivationLayer(dec.output_shape, 'lrelu', subnet + '_act8', alpha=self.alpha))
dec.append(nn.ConvolutionalLayer(dec.output_shape, 3, 5, activation='tanh', no_bias=False,
layer_name=subnet + '_output'))
self.model.append(dec)
def __init__(self,
input_shape,
n_nodes,
use_sigmoid=False,
name='Latent Discriminator'):
super(DiscriminatorLatent, self).__init__(input_shape=input_shape,
layer_name=name)
self.append(
nn.FCLayer(self.output_shape,
n_nodes,
activation=None,
layer_name=name + '/fc1'))
self.append(
nn.BatchNormLayer(self.output_shape,
name + '/bn1',
activation='lrelu',
alpha=.2))
self.append(
nn.FCLayer(self.output_shape,
n_nodes,
activation=None,
layer_name=name + '/fc2'))
self.append(
nn.BatchNormLayer(self.output_shape,
name + '/bn2',
activation='lrelu',
alpha=.2))
self.append(
nn.FCLayer(self.output_shape,
n_nodes,
activation=None,
layer_name=name + '/fc3'))
self.append(
nn.BatchNormLayer(self.output_shape,
name + '/bn3',
activation='lrelu',
alpha=.2))
self.append(
nn.FCLayer(self.output_shape,
1,
activation=None,
layer_name=name + '/output'))
if use_sigmoid:
self.append(
nn.ActivationLayer(self.output_shape, 'sigmoid',
name + '/act'))
def __init__(self,
input_shape,
n_latent,
num_filters,
norm_layer,
deterministic=False,
use_bias=False,
name='Latent Encoder'):
super(LatentEncoder, self).__init__(input_shape=input_shape,
layer_name=name)
self.deterministic = deterministic
self.enc = nn.Sequential(input_shape=input_shape,
layer_name=name + '/enc')
self.enc.append(
nn.Conv2DLayer(self.enc.output_shape,
num_filters,
3,
stride=2,
no_bias=False,
activation='relu',
layer_name=name + '/conv1'))
self.enc.append(
nn.Conv2DLayer(self.enc.output_shape,
2 * num_filters,
3,
stride=2,
no_bias=not use_bias,
activation=None,
layer_name=name + '/conv2'))
self.enc.append(norm_layer(self.enc.output_shape, name + '/norm2'))
self.enc.append(
nn.ActivationLayer(self.enc.output_shape, 'relu', name + '/act2'))
self.enc.append(
nn.Conv2DLayer(self.enc.output_shape,
4 * num_filters,
3,
stride=2,
no_bias=not use_bias,
activation=None,
layer_name=name + '/conv3'))
self.enc.append(norm_layer(self.enc.output_shape, name + '/norm3'))
self.enc.append(
nn.ActivationLayer(self.enc.output_shape, 'relu', name + '/act3'))
self.enc.append(
nn.Conv2DLayer(self.enc.output_shape,
8 * num_filters,
3,
stride=2,
no_bias=not use_bias,
activation=None,
layer_name=name + '/conv4'))
self.enc.append(norm_layer(self.enc.output_shape, name + '/norm4'))
self.enc.append(
nn.ActivationLayer(self.enc.output_shape, 'relu', name + '/act4'))
self.enc.append(
nn.Conv2DLayer(self.enc.output_shape,
8 * num_filters,
4,
stride=1,
no_bias=not use_bias,
activation=None,
border_mode='valid',
layer_name=name + '/conv5'))
self.enc.append(norm_layer(self.enc.output_shape, name + '/norm5'))
self.enc.append(
nn.ActivationLayer(self.enc.output_shape, 'relu', name + '/act5'))
self.enc_mu = nn.Conv2DLayer(self.enc.output_shape,
n_latent,
1,
no_bias=False,
activation=None,
layer_name=name + '/mu')
self.extend((self.enc, self.enc_mu))
if not deterministic:
self.enc_logvar = nn.Conv2DLayer(self.enc.output_shape,
n_latent,
1,
no_bias=False,
activation=None,
layer_name=name + '/logvar')
self.append(self.enc_logvar)
def __init__(self,
input_shape,
num_filters=64,
norm_layer=partial(nn.BatchNormLayer, activation=None),
use_sigmoid=False,
use_bias=True,
name='Discriminator Edges'):
super(DiscriminatorEdges, self).__init__(input_shape=input_shape,
layer_name=name)
self.append(
nn.Conv2DLayer(self.output_shape,
num_filters,
3,
stride=2,
border_mode='half',
no_bias=not use_bias,
activation='lrelu',
alpha=.2,
layer_name=name + '/conv1'))
self.append(
nn.Conv2DLayer(self.output_shape,
2 * num_filters,
3,
stride=2,
border_mode='half',
no_bias=not use_bias,
activation=None,
layer_name=name + '/conv2'))
self.append(norm_layer(self.output_shape, name + '/bn2'))
self.append(
nn.ActivationLayer(self.output_shape,
activation='lrelu',
alpha=.2,
layer_name=name + '/act2'))
self.append(
nn.Conv2DLayer(self.output_shape,
4 * num_filters,
3,
border_mode='half',
no_bias=not use_bias,
activation=None,
layer_name=name + '/conv3'))
self.append(norm_layer(self.output_shape, layer_name=name + '/bn3'))
self.append(
nn.ActivationLayer(self.output_shape,
activation='lrelu',
alpha=.2,
layer_name=name + '/act3'))
self.append(
nn.Conv2DLayer(self.output_shape,
4 * num_filters,
3,
border_mode='half',
no_bias=not use_bias,
activation=None,
layer_name=name + '/conv4'))
self.append(norm_layer(self.output_shape, layer_name=name + '/bn4'))
self.append(
nn.ActivationLayer(self.output_shape,
activation='lrelu',
alpha=.2,
layer_name=name + '/act4'))
self.append(
nn.Conv2DLayer(self.output_shape,
1,
4,
border_mode='valid',
layer_name=name + '/output',
activation=None))
if use_sigmoid:
self.append(
nn.ActivationLayer(self.output_shape, 'sigmoid',
name + '/sigmoid'))
def __init__(self,
input_shape,
n_latent,
num_filters=64,
norm_layer=nn.ConditionalInstanceNorm2DLayer,
use_sigmoid=False,
use_bias=True,
name='CIN Discriminator'):
super(CINDiscriminator, self).__init__(input_shape=input_shape,
layer_name=name)
self.append(
nn.Conv2DLayer(self.output_shape,
num_filters,
4,
stride=2,
border_mode=1,
no_bias=not use_bias,
activation='lrelu',
alpha=.2,
layer_name=name + '/conv1'))
self.append(
nn.Conv2DLayer(self.output_shape,
2 * num_filters,
4,
stride=2,
border_mode=1,
no_bias=not use_bias,
activation=None,
layer_name=name + '/conv2'))
self.append(norm_layer(self.output_shape, n_latent, name + '/bn2'))
self.append(
nn.ActivationLayer(self.output_shape,
activation='lrelu',
alpha=.2,
layer_name=name + '/act2'))
self.append(
nn.Conv2DLayer(self.output_shape,
4 * num_filters,
4,
border_mode=1,
no_bias=not use_bias,
activation=None,
layer_name=name + '/conv3'))
self.append(
norm_layer(self.output_shape, n_latent, layer_name=name + '/bn3'))
self.append(
nn.ActivationLayer(self.output_shape,
activation='lrelu',
alpha=.2,
layer_name=name + '/act3'))
self.append(
nn.Conv2DLayer(self.output_shape,
5 * num_filters,
4,
border_mode=1,
no_bias=not use_bias,
activation=None,
layer_name=name + '/conv4'))
self.append(
norm_layer(self.output_shape, n_latent, layer_name=name + '/bn4'))
self.append(
nn.ActivationLayer(self.output_shape,
activation='lrelu',
alpha=.2,
layer_name=name + '/act4'))
self.append(
nn.Conv2DLayer(self.output_shape,
1,
4,
border_mode=1,
layer_name=name + '/output',
activation=None))
if use_sigmoid:
self.append(
nn.ActivationLayer(self.output_shape, 'sigmoid',
name + '/sigmoid'))
def __init__(self,
input_shape,
num_filters,
output_dim,
norm_layer=partial(nn.InstanceNormLayer, activation=None),
use_dropout=False,
padding='ref',
name='Resnet Generator'):
super(ResnetGen, self).__init__(input_shape=input_shape,
layer_name=name)
self.append(
nn.Conv2DLayer(input_shape,
num_filters,
7,
border_mode='ref',
activation=None,
no_bias=False,
layer_name=name + '/conv1'))
self.append(norm_layer(self.output_shape, layer_name=name + '/cin1'))
self.append(
nn.ActivationLayer(self.output_shape,
'relu',
layer_name=name + '/relu1'))
self.append(
nn.Conv2DLayer(self.output_shape,
num_filters * 2,
3,
border_mode='half',
activation=None,
no_bias=False,
layer_name=name + '/conv2'))
self.append(norm_layer(self.output_shape, layer_name=name + '/cin2'))
self.append(
nn.ActivationLayer(self.output_shape,
'relu',
layer_name=name + '/relu2'))
self.append(
nn.Conv2DLayer(self.output_shape,
num_filters * 4,
3,
stride=2,
border_mode='half',
activation=None,
no_bias=False,
layer_name=name + '/conv3'))
self.append(norm_layer(self.output_shape, layer_name=name + '/cin3'))
self.append(
nn.ActivationLayer(self.output_shape,
'relu',
layer_name=name + '/relu3'))
for i in range(3):
self.append(
ResnetBlock(self.output_shape, padding, norm_layer,
use_dropout, True,
name + '/ResBlock %d' % (i + 1)))
self.append(
nn.TransposedConvolutionalLayer(self.output_shape,
2 * num_filters,
3,
stride=(2, 2),
padding='half',
activation=None,
layer_name=name + '/deconv'))
self.append(norm_layer(self.output_shape, layer_name=name + '/cin4'))
self.append(
nn.ActivationLayer(self.output_shape, 'relu', name + '/relu4'))
self.append(
nn.Conv2DLayer(self.output_shape,
num_filters,
3,
border_mode='half',
activation=None,
no_bias=False,
layer_name=name + '/conv5'))
self.append(norm_layer(self.output_shape, layer_name=name + '/cin5'))
self.append(
nn.ActivationLayer(self.output_shape,
'relu',
layer_name=name + '/relu5'))
self.append(
nn.Conv2DLayer(self.output_shape,
output_dim,
7,
activation=None,
layer_name=name + '/output'))
self.append(
nn.ActivationLayer(self.output_shape,
'tanh',
layer_name=name + '/output_act'))
def __init__(self,
input_shape,
num_classes=10,
name='vgg19 mean interp padding'):
super(VGG19MeanInterpPadding, self).__init__(input_shape=input_shape,
layer_name=name)
self.append(
Conv2DMeanInterpPaddingLayer(self.output_shape,
64,
3,
activation=None,
layer_name=name + '/conv1'))
self.append(nn.BatchNormLayer(self.output_shape, name + '/bn1'))
self.append(
Conv2DMeanInterpPaddingLayer(self.output_shape,
64,
3,
activation=None,
layer_name=name + '/conv2'))
self.append(
nn.BatchNormLayer(self.output_shape,
name + '/bn2',
activation=None))
self.append(
nn.MaxPoolingLayer(self.output_shape, (2, 2),
layer_name=name + '/maxpool0'))
self.append(
nn.ActivationLayer(self.output_shape, 'relu', name + '/relu2'))
self.append(
Conv2DMeanInterpPaddingLayer(self.output_shape,
128,
3,
activation=None,
layer_name=name + '/conv3'))
self.append(nn.BatchNormLayer(self.output_shape, name + '/bn3'))
self.append(
Conv2DMeanInterpPaddingLayer(self.output_shape,
128,
3,
activation=None,
layer_name=name + '/conv4'))
self.append(
nn.BatchNormLayer(self.output_shape,
name + '/bn4',
activation=None))
self.append(
nn.MaxPoolingLayer(self.output_shape, (2, 2),
layer_name=name + '/maxpool1'))
self.append(
nn.ActivationLayer(self.output_shape, 'relu', name + '/relu4'))
self.append(
Conv2DMeanInterpPaddingLayer(self.output_shape,
256,
3,
activation=None,
layer_name=name + '/conv5'))
self.append(nn.BatchNormLayer(self.output_shape, name + '/bn5'))
self.append(
Conv2DMeanInterpPaddingLayer(self.output_shape,
256,
3,
activation=None,
layer_name=name + '/conv6'))
self.append(nn.BatchNormLayer(self.output_shape, name + '/bn6'))
self.append(
Conv2DMeanInterpPaddingLayer(self.output_shape,
256,
3,
activation=None,
layer_name=name + '/conv7'))
self.append(nn.BatchNormLayer(self.output_shape, name + '/bn7'))
self.append(
Conv2DMeanInterpPaddingLayer(self.output_shape,
256,
3,
activation=None,
layer_name=name + '/conv7_1'))
self.append(
nn.BatchNormLayer(self.output_shape,
name + '/bn7_1',
activation=None))
self.append(
nn.MaxPoolingLayer(self.output_shape, (2, 2),
layer_name=name + '/maxpool2'))
self.append(
nn.ActivationLayer(self.output_shape, 'relu', name + '/relu8'))
self.append(
Conv2DMeanInterpPaddingLayer(self.output_shape,
512,
3,
activation=None,
layer_name=name + '/conv8'))
self.append(nn.BatchNormLayer(self.output_shape, name + '/bn8'))
self.append(
Conv2DMeanInterpPaddingLayer(self.output_shape,
512,
3,
activation=None,
layer_name=name + '/conv9'))
self.append(nn.BatchNormLayer(self.output_shape, name + '/bn9'))
self.append(
Conv2DMeanInterpPaddingLayer(self.output_shape,
512,
3,
activation=None,
layer_name=name + '/conv10'))
self.append(nn.BatchNormLayer(self.output_shape, name + '/bn10'))
self.append(
Conv2DMeanInterpPaddingLayer(self.output_shape,
512,
3,
activation=None,
layer_name=name + '/conv10_1'))
self.append(
nn.BatchNormLayer(self.output_shape,
name + '/bn10_1',
activation=None))
self.append(
nn.MaxPoolingLayer(self.output_shape, (2, 2),
layer_name=name + '/maxpool3'))
self.append(
nn.ActivationLayer(self.output_shape, 'relu', name + '/relu11'))
self.append(
Conv2DMeanInterpPaddingLayer(self.output_shape,
512,
3,
activation=None,
layer_name=name + '/conv11'))
self.append(nn.BatchNormLayer(self.output_shape, name + '/bn11'))
self.append(
Conv2DMeanInterpPaddingLayer(self.output_shape,
512,
3,
activation=None,
layer_name=name + '/conv12'))
self.append(nn.BatchNormLayer(self.output_shape, name + '/bn12'))
self.append(
Conv2DMeanInterpPaddingLayer(self.output_shape,
512,
3,
activation=None,
layer_name=name + '/conv13'))
self.append(nn.BatchNormLayer(self.output_shape, name + '/bn13'))
self.append(
Conv2DMeanInterpPaddingLayer(self.output_shape,
512,
3,
activation=None,
layer_name=name + '/conv13_1'))
self.append(
nn.BatchNormLayer(self.output_shape,
name + '/bn13_1',
activation=None))
self.append(
nn.MaxPoolingLayer(self.output_shape, (2, 2),
layer_name=name + '/maxpool4'))
self.append(
nn.ActivationLayer(self.output_shape, 'relu', name + '/relu14'))
self.append(
nn.SoftmaxLayer(self.output_shape, num_classes, name + '/softmax'))