def _build_simple_conv_block(input_shape, num_filters, stride, border_mode,
activation, block_name, **kwargs):
block = [
nn.Conv2DLayer(input_shape,
num_filters,
3,
stride=stride,
border_mode=border_mode,
layer_name=block_name + '/conv1',
no_bias=False,
activation='linear')
]
block.append(
nn.BatchNormLayer(block[-1].output_shape,
activation=activation,
layer_name=block_name + '/conv1_bn'))
block.append(
nn.Conv2DLayer(block[-1].output_shape,
num_filters,
3,
border_mode=border_mode,
no_bias=True,
layer_name=block_name + '/conv2',
activation='linear'))
block.append(
nn.BatchNormLayer(block[-1].output_shape,
layer_name=block_name + '/conv2_bn',
activation='linear'))
return block
def _build_mean_ref_pad_conv_block(input_shape, num_filters, stride,
activation, block_name, **kwargs):
block = [
Conv2DMeanRefPaddingLayer(input_shape,
num_filters,
3,
stride=stride,
layer_name=block_name + '/conv1',
no_bias=False,
activation='linear')
]
block.append(
nn.BatchNormLayer(block[-1].output_shape,
activation=activation,
layer_name=block_name + '/conv1_bn'))
block.append(
Conv2DMeanRefPaddingLayer(block[-1].output_shape,
num_filters,
3,
layer_name=block_name + '/conv2',
no_bias=True,
activation='linear'))
block.append(
nn.BatchNormLayer(block[-1].output_shape,
layer_name=block_name + '/conv2_bn',
activation='linear'))
return block
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,
fc=True,
num_classes=1000,
first_output=16,
growth_rate=12,
num_blocks=3,
depth=40,
dropout=False,
name='DenseNet'):
super(DenseNet, self).__init__(input_shape=input_shape,
layer_name=name)
self.append(
nn.ConvolutionalLayer(self.input_shape,
first_output,
3,
activation='linear',
layer_name=name + 'pre_conv'))
n = (depth - 1) // num_blocks
for b in range(num_blocks):
self.append(
nn.DenseBlock(self.output_shape,
num_conv_layer=n - 1,
growth_rate=growth_rate,
dropout=dropout,
layer_name=name + 'dense_block_%d' % b))
if b < num_blocks - 1:
self.append(
nn.DenseBlock(self.output_shape,
True,
None,
None,
dropout,
layer_name=name +
'dense_block_transit_%d' % b))
self.append(
nn.BatchNormLayer(self.output_shape, layer_name=name + 'post_bn'))
if fc:
self.append(
nn.GlobalAveragePoolingLayer(input_shape,
name + '_glbavgpooling'))
self.append(
nn.SoftmaxLayer(self.output_shape, num_classes,
name + '_softmax'))
def __init__(self,
input_shape,
bottom_width=4,
ch=512,
wscale=0.02,
hidden_activation='relu',
output_activation='tanh',
layer_name='DCGANGen'):
super(DCGANGenerator, self).__init__(input_shape=input_shape,
layer_name=layer_name)
self.append(
nn.FullyConnectedLayer(self.output_shape,
ch * bottom_width**2,
layer_name=layer_name + '/fc1',
activation='linear',
init=nn.Normal(wscale)))
self.append(
nn.BatchNormLayer(self.output_shape,
layer_name + '/bn_fc1',
activation=hidden_activation,
epsilon=2e-5))
self.append(
nn.ReshapingLayer(self.output_shape,
(-1, ch, bottom_width, bottom_width),
layer_name + '/reshape'))
shape = [o * 2 for o in self.output_shape[2:]]
self.append(
nn.TransposedConvolutionalLayer(self.output_shape,
ch // 2,
4,
shape,
layer_name=layer_name + '/deconv1',
padding=1,
activation='linear',
init=nn.Normal(wscale)))
self.append(
nn.BatchNormLayer(self.output_shape,
layer_name + '/bn_deconv1',
activation=hidden_activation,
epsilon=2e-5))
shape = [o * 2 for o in self.output_shape[2:]]
self.append(
nn.TransposedConvolutionalLayer(self.output_shape,
ch // 4,
4,
shape,
layer_name=layer_name + '/deconv2',
padding=1,
activation='linear',
init=nn.Normal(wscale)))
self.append(
nn.BatchNormLayer(self.output_shape,
layer_name + '/bn_deconv2',
activation=hidden_activation,
epsilon=2e-5))
shape = [o * 2 for o in self.output_shape[2:]]
self.append(
nn.TransposedConvolutionalLayer(self.output_shape,
ch // 8,
4,
shape,
layer_name=layer_name + '/deconv3',
padding=1,
activation='linear',
init=nn.Normal(wscale)))
self.append(
nn.BatchNormLayer(self.output_shape,
layer_name + '/bn_deconv3',
activation=hidden_activation,
epsilon=2e-5))
self.append(
nn.TransposedConvolutionalLayer(self.output_shape,
3,
3,
layer_name=layer_name + '/output',
stride=(1, 1),
activation=output_activation,
init=nn.Normal(wscale)))
def __init__(self,
input_shape,
fc=True,
bn=False,
dropout=True,
border_mode='half',
num_classes=1000,
name='vgg16'):
super(VGG16, self).__init__(input_shape=input_shape, layer_name=name)
self.fc = fc
self.append(
nn.Conv2DLayer(self.output_shape,
64,
3,
nn.HeNormal('relu'),
activation=None,
no_bias=False,
layer_name=name + '/conv1',
border_mode=border_mode))
self.append(
nn.BatchNormLayer(self.output_shape, name + '/bn1') if bn else nn.
ActivationLayer(self.output_shape, layer_name=name + '/relu1'))
self.append(
nn.Conv2DLayer(self.output_shape,
64,
3,
nn.HeNormal('relu'),
activation=None,
no_bias=False,
layer_name=name + '/conv2',
border_mode=border_mode))
self.append(
nn.BatchNormLayer(self.output_shape, name + '/bn2') if bn else nn.
ActivationLayer(self.output_shape, layer_name=name + '/relu2'))
self.append(
nn.MaxPoolingLayer(self.output_shape, (2, 2),
layer_name=name + '_maxpool0'))
self.append(
nn.Conv2DLayer(self.output_shape,
128,
3,
nn.HeNormal('relu'),
activation=None,
no_bias=False,
layer_name=name + '/conv3',
border_mode=border_mode))
self.append(
nn.BatchNormLayer(self.output_shape, name + '/bn3') if bn else nn.
ActivationLayer(self.output_shape, layer_name=name + '/relu3'))
self.append(
nn.Conv2DLayer(self.output_shape,
128,
3,
nn.HeNormal('relu'),
activation=None,
no_bias=False,
layer_name=name + '/conv4',
border_mode=border_mode))
self.append(
nn.BatchNormLayer(self.output_shape, name + '/bn4') if bn else nn.
ActivationLayer(self.output_shape, layer_name=name + '/relu4'))
self.append(
nn.MaxPoolingLayer(self.output_shape, (2, 2),
layer_name=name + '_maxpool1'))
self.append(
nn.Conv2DLayer(self.output_shape,
256,
3,
nn.HeNormal('relu'),
activation=None,
no_bias=False,
layer_name=name + '/conv5',
border_mode=border_mode))
self.append(
nn.BatchNormLayer(self.output_shape, name + '/bn5') if bn else nn.
ActivationLayer(self.output_shape, layer_name=name + '/relu5'))
self.append(
nn.Conv2DLayer(self.output_shape,
256,
3,
nn.HeNormal('relu'),
activation=None,
no_bias=False,
layer_name=name + '/conv6',
border_mode=border_mode))
self.append(
nn.BatchNormLayer(self.output_shape, name + '/bn6') if bn else nn.
ActivationLayer(self.output_shape, layer_name=name + '/relu6'))
self.append(
nn.Conv2DLayer(self.output_shape,
256,
3,
nn.HeNormal('relu'),
activation=None,
no_bias=False,
layer_name=name + '/conv7',
border_mode=border_mode))
self.append(
nn.BatchNormLayer(self.output_shape, name + '/bn7') if bn else nn.
ActivationLayer(self.output_shape, layer_name=name + '/relu7'))
self.append(
nn.MaxPoolingLayer(self.output_shape, (2, 2),
layer_name=name + '_maxpool2'))
self.append(
nn.Conv2DLayer(self.output_shape,
512,
3,
nn.HeNormal('relu'),
activation=None,
no_bias=False,
layer_name=name + '/conv8',
border_mode=border_mode))
self.append(
nn.BatchNormLayer(self.output_shape, name + '/bn8') if bn else nn.
ActivationLayer(self.output_shape, layer_name=name + '/relu8'))
self.append(
nn.Conv2DLayer(self.output_shape,
512,
3,
nn.HeNormal('relu'),
activation=None,
no_bias=False,
layer_name=name + '/conv9',
border_mode=border_mode))
self.append(
nn.BatchNormLayer(self.output_shape, name + '/bn9') if bn else nn.
ActivationLayer(self.output_shape, layer_name=name + '/relu9'))
self.append(
nn.Conv2DLayer(self.output_shape,
512,
3,
nn.HeNormal('relu'),
activation=None,
no_bias=False,
layer_name=name + '/conv10',
border_mode=border_mode))
self.append(
nn.BatchNormLayer(self.output_shape, name + '/bn10') if bn else nn.
ActivationLayer(self.output_shape, layer_name=name + '/relu10'))
self.append(
nn.MaxPoolingLayer(self.output_shape, (2, 2),
layer_name=name + '_maxpool3'))
self.append(
nn.Conv2DLayer(self.output_shape,
512,
3,
nn.HeNormal('relu'),
activation=None,
no_bias=False,
layer_name=name + '/conv11',
border_mode=border_mode))
self.append(
nn.BatchNormLayer(self.output_shape, name + '/bn11') if bn else nn.
ActivationLayer(self.output_shape, layer_name=name + '/relu11'))
self.append(
nn.Conv2DLayer(self.output_shape,
512,
3,
nn.HeNormal('relu'),
activation=None,
no_bias=False,
layer_name=name + '/conv12',
border_mode=border_mode))
self.append(
nn.BatchNormLayer(self.output_shape, name + '/bn11') if bn else nn.
ActivationLayer(self.output_shape, layer_name=name + '/relu12'))
self.append(
nn.Conv2DLayer(self.output_shape,
512,
3,
nn.HeNormal('relu'),
activation=None,
no_bias=False,
layer_name=name + '/conv13',
border_mode=border_mode))
self.append(
nn.BatchNormLayer(self.output_shape, name + '/bn13') if bn else nn.
ActivationLayer(self.output_shape, layer_name=name + '/relu13'))
if fc:
self.append(
nn.MaxPoolingLayer(self.output_shape, (2, 2),
layer_name=name + '_maxpool4'))
self.append(
nn.FCLayer(self.output_shape, 4096, layer_name=name + '_fc1'))
if dropout:
self.append(
nn.DropoutLayer(self.output_shape,
drop_prob=.5,
layer_name=name + '/dropout1'))
self.append(
nn.FCLayer(self.output_shape, 4096, layer_name=name + '_fc2'))
if dropout:
self.append(
nn.DropoutLayer(self.output_shape,
drop_prob=.5,
layer_name=name + '/dropout2'))
self.append(
nn.SoftmaxLayer(self.output_shape, num_classes,
name + '_softmax'))
def __init__(self, input_shape, output_size):
super(LSGAN, self).__init__(input_shape=input_shape,
layer_name='LSGAN')
s2, s4, s8, s16 = output_size // 2, output_size // 4, output_size // 8, output_size // 16
subnet = 'generator'
self.gen = nn.Sequential(input_shape=input_shape, layer_name=subnet)
self.gen.append(
nn.FullyConnectedLayer(self.gen.output_shape,
256 * s16 * s16,
activation='linear',
layer_name=subnet + '/fc1',
init=nn.Normal(.02)))
self.gen.append(
nn.ReshapingLayer(self.gen.output_shape, (-1, 256, s16, s16),
subnet + '/reshape'))
self.gen.append(
nn.BatchNormLayer(self.gen.output_shape,
subnet + '/bn1',
activation='relu',
epsilon=1.1e-5))
self.gen.append(
nn.TransposedConvolutionalLayer(self.gen.output_shape,
256,
3, (s8, s8),
activation='linear',
layer_name=subnet + '/deconv1',
init=nn.Normal(.02)))
self.gen.append(
nn.BatchNormLayer(self.gen.output_shape,
subnet + '/bn2',
activation='relu',
epsilon=1.1e-5))
self.gen.append(
nn.TransposedConvolutionalLayer(self.gen.output_shape,
256,
3, (s8, s8),
stride=(1, 1),
activation='linear',
layer_name=subnet + '/deconv2',
init=nn.Normal(.02)))
self.gen.append(
nn.BatchNormLayer(self.gen.output_shape,
subnet + '/bn3',
activation='relu',
epsilon=1.1e-5))
self.gen.append(
nn.TransposedConvolutionalLayer(self.gen.output_shape,
256,
3, (s4, s4),
activation='linear',
layer_name=subnet + '/deconv3',
init=nn.Normal(.02)))
self.gen.append(
nn.BatchNormLayer(self.gen.output_shape,
subnet + '/bn4',
activation='relu',
epsilon=1.1e-5))
self.gen.append(
nn.TransposedConvolutionalLayer(self.gen.output_shape,
256,
3, (s4, s4),
stride=(1, 1),
activation='linear',
layer_name=subnet + '/deconv4',
init=nn.Normal(.02)))
self.gen.append(
nn.BatchNormLayer(self.gen.output_shape,
subnet + '/bn5',
activation='relu',
epsilon=1.1e-5))
self.gen.append(
nn.TransposedConvolutionalLayer(self.gen.output_shape,
128,
3, (s2, s2),
activation='linear',
layer_name=subnet + '/deconv5',
init=nn.Normal(.02)))
self.gen.append(
nn.BatchNormLayer(self.gen.output_shape,
subnet + '/bn6',
activation='relu',
epsilon=1.1e-5))
self.gen.append(
nn.TransposedConvolutionalLayer(self.gen.output_shape,
64,
3, (output_size, output_size),
activation='linear',
layer_name=subnet + '/deconv6',
init=nn.Normal(.02)))
self.gen.append(
nn.BatchNormLayer(self.gen.output_shape,
subnet + '/bn7',
activation='relu',
epsilon=1.1e-5))
self.gen.append(
nn.TransposedConvolutionalLayer(self.gen.output_shape,
3,
3, (output_size, output_size),
stride=(1, 1),
activation='tanh',
layer_name=subnet + '/output',
init=nn.Normal(.02)))
self.append(self.gen)
subnet = 'discriminator'
self.dis = nn.Sequential(input_shape=self.gen.output_shape,
layer_name=subnet)
self.dis.append(
nn.ConvolutionalLayer(self.dis.output_shape,
64,
5,
stride=2,
activation='lrelu',
no_bias=False,
layer_name=subnet + '/first_conv',
init=nn.TruncatedNormal(.02),
alpha=.2))
self.dis.append(
nn.ConvNormAct(self.dis.output_shape,
64 * 2,
5,
stride=2,
activation='lrelu',
no_bias=False,
layer_name=subnet + '/conv1',
init=nn.TruncatedNormal(.02),
epsilon=1.1e-5,
alpha=.2))
self.dis.append(
nn.ConvNormAct(self.dis.output_shape,
64 * 4,
5,
stride=2,
activation='lrelu',
no_bias=False,
layer_name=subnet + '/conv2',
init=nn.TruncatedNormal(.02),
epsilon=1.1e-5,
alpha=.2))
self.dis.append(
nn.ConvNormAct(self.dis.output_shape,
64 * 8,
5,
stride=2,
activation='lrelu',
no_bias=False,
layer_name=subnet + '/conv3',
init=nn.TruncatedNormal(.02),
epsilon=1.1e-5,
alpha=.2))
self.dis.append(
nn.FullyConnectedLayer(self.dis.output_shape,
1,
layer_name=subnet + '/output',
activation='linear'))
self.append(self.dis)
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'))