我们从Python开源项目中，提取了以下47个代码示例，用于说明如何使用chainer.links.Deconvolution2D()。
def __init__(self): super(FastStyleNet, self).__init__( c1=L.Convolution2D(3, 32, 9, stride=1, pad=4), c2=L.Convolution2D(32, 64, 4, stride=2, pad=1), c3=L.Convolution2D(64, 128, 4,stride=2, pad=1), r1=ResidualBlock(128, 128), r2=ResidualBlock(128, 128), r3=ResidualBlock(128, 128), r4=ResidualBlock(128, 128), r5=ResidualBlock(128, 128), d1=L.Deconvolution2D(128, 64, 4, stride=2, pad=1), d2=L.Deconvolution2D(64, 32, 4, stride=2, pad=1), d3=L.Deconvolution2D(32, 3, 9, stride=1, pad=4), b1=L.BatchNormalization(32), b2=L.BatchNormalization(64), b3=L.BatchNormalization(128), b4=L.BatchNormalization(64), b5=L.BatchNormalization(32), )
def __init__(self, n_hidden, bottom_width=4, ch=512, wscale=0.02): super(Generator, self).__init__() self.n_hidden = n_hidden self.ch = ch self.bottom_width = bottom_width with self.init_scope(): w = chainer.initializers.Normal(wscale) self.l0 = L.Linear(self.n_hidden, bottom_width * bottom_width * ch, initialW=w) self.dc1 = L.Deconvolution2D(ch, ch // 2, 4, 2, 1, initialW=w) self.dc2 = L.Deconvolution2D(ch // 2, ch // 4, 4, 2, 1, initialW=w) self.dc3 = L.Deconvolution2D(ch // 4, ch // 8, 4, 2, 1, initialW=w) self.dc4 = L.Deconvolution2D(ch // 8, 3, 3, 1, 1, initialW=w) self.bn0 = L.BatchNormalization(bottom_width * bottom_width * ch) self.bn1 = L.BatchNormalization(ch // 2) self.bn2 = L.BatchNormalization(ch // 4) self.bn3 = L.BatchNormalization(ch // 8)
def setUp(self): self.link = L.Deconvolution2D( self.in_channels, self.out_channels, self.ksize, stride=self.stride, pad=self.pad, nobias=self.nobias) self.link.W.data[...] = numpy.random.uniform( -1, 1, self.link.W.data.shape).astype(numpy.float32) if not self.nobias: self.link.b.data[...] = numpy.random.uniform( -1, 1, self.link.b.data.shape).astype(numpy.float32) self.link.zerograds() N = 2 h, w = 3, 2 kh, kw = _pair(self.ksize) out_h = conv.get_deconv_outsize(h, kh, self.stride, self.pad) out_w = conv.get_deconv_outsize(w, kw, self.stride, self.pad) self.gy = numpy.random.uniform( -1, 1, (N, self.out_channels, out_h, out_w)).astype(numpy.float32) self.x = numpy.random.uniform( -1, 1, (N, self.in_channels, h, w)).astype(numpy.float32)
def __init__(self, n_hidden=128, bottom_width=4, ch=512, wscale=0.02): super(Generator, self).__init__() self.n_hidden = n_hidden self.ch = ch self.bottom_width = bottom_width with self.init_scope(): w = chainer.initializers.Normal(wscale) self.l0 = L.Linear(self.n_hidden, bottom_width*bottom_width*ch, initialW=w) self.dc1 = L.Deconvolution2D(ch, ch//2, 4, 2, 1, initialW=w) self.dc2 = L.Deconvolution2D(ch//2, ch//4, 4, 2, 1, initialW=w) self.dc3 = L.Deconvolution2D(ch//4, ch//8, 4, 2, 1, initialW=w) self.dc4 = L.Deconvolution2D(ch//8, 3, 3, 1, 1, initialW=w) self.bn0 = L.BatchNormalization(bottom_width*bottom_width*ch) self.bn1 = L.BatchNormalization(ch//2) self.bn2 = L.BatchNormalization(ch//4) self.bn3 = L.BatchNormalization(ch//8)
def __init__(self, n_hidden, activate='sigmoid', size=64, ch=512, wscale=0.02): assert (size % 16 == 0) initial_size = size // 16 self.n_hidden = n_hidden if activate == 'sigmoid': self.activate = F.sigmoid elif activate == 'tanh': self.activate = F.tanh else: raise ValueError('invalid activate function') self.ch = ch self.initial_size = initial_size w = chainer.initializers.Normal(wscale) super(Generator, self).__init__( l0=L.Linear(self.n_hidden, initial_size * initial_size * ch, initialW=w), dc1=L.Deconvolution2D(ch // 1, ch // 2, 4, 2, 1, initialW=w), dc2=L.Deconvolution2D(ch // 2, ch // 4, 4, 2, 1, initialW=w), dc3=L.Deconvolution2D(ch // 4, ch // 8, 4, 2, 1, initialW=w), dc4=L.Deconvolution2D(ch // 8, 3, 4, 2, 1, initialW=w), bn0=L.BatchNormalization(initial_size * initial_size * ch), bn1=L.BatchNormalization(ch // 2), bn2=L.BatchNormalization(ch // 4), bn3=L.BatchNormalization(ch // 8), )
def __init__(self, n_hidden, activate='sigmoid', size=64, ch=512, wscale=0.02): assert (size % 8 == 0) initial_size = size // 8 self.n_hidden = n_hidden self.ch = ch self.initial_size = initial_size if activate == 'sigmoid': self.activate = F.sigmoid elif activate == 'tanh': self.activate = F.tanh else: raise ValueError('invalid activate function') w = chainer.initializers.Normal(wscale) super(Generator2, self).__init__( l0=L.Linear(self.n_hidden, initial_size * initial_size * ch, initialW=w), dc1=L.Deconvolution2D(ch // 1, ch // 2, 4, 2, 1, initialW=w), dc2=L.Deconvolution2D(ch // 2, ch // 4, 4, 2, 1, initialW=w), dc3=L.Deconvolution2D(ch // 4, ch // 8, 4, 2, 1, initialW=w), dc4=L.Deconvolution2D(ch // 8, 3, 3, 1, 1, initialW=w), bn0=L.BatchNormalization(initial_size * initial_size * ch), bn1=L.BatchNormalization(ch // 2), bn2=L.BatchNormalization(ch // 4), bn3=L.BatchNormalization(ch // 8), )
def __init__(self, n_hidden, activate='sigmoid', size=64, ch=512, wscale=0.02): assert (size % 8 == 0) initial_size = size // 8 self.n_hidden = n_hidden if activate == 'sigmoid': self.activate = F.sigmoid elif activate == 'tanh': self.activate = F.tanh else: raise ValueError('invalid activate function') self.ch = ch self.initial_size = initial_size w = chainer.initializers.Normal(wscale) super(Generator, self).__init__( l0=L.Linear(self.n_hidden, initial_size * initial_size * ch, initialW=w), dc1=L.Deconvolution2D(ch // 1, ch // 2, 4, 2, 1, initialW=w), dc2=L.Deconvolution2D(ch // 2, ch // 4, 4, 2, 1, initialW=w), dc3=L.Deconvolution2D(ch // 4, ch // 8, 4, 2, 1, initialW=w), dc4=L.Deconvolution2D(ch // 8, 3, 3, 1, 1, initialW=w), )
def __init__(self, density=1, size=64, latent_size=128, channel=3): assert (size % 16 == 0) initial_size = size / 16 super(Generator, self).__init__( g1=L.Linear(latent_size, initial_size * initial_size * 256 * density, wscale=0.02 * math.sqrt(latent_size)), norm1=L.BatchNormalization(initial_size * initial_size * 256 * density), g2=L.Deconvolution2D(256 * density, 128 * density, 4, stride=2, pad=1, wscale=0.02 * math.sqrt(4 * 4 * 256 * density)), norm2=L.BatchNormalization(128 * density), g3=L.Deconvolution2D(128 * density, 64 * density, 4, stride=2, pad=1, wscale=0.02 * math.sqrt(4 * 4 * 128 * density)), norm3=L.BatchNormalization(64 * density), g4=L.Deconvolution2D(64 * density, 32 * density, 4, stride=2, pad=1, wscale=0.02 * math.sqrt(4 * 4 * 64 * density)), norm4=L.BatchNormalization(32 * density), g5=L.Deconvolution2D(32 * density, channel, 4, stride=2, pad=1, wscale=0.02 * math.sqrt(4 * 4 * 32 * density)), ) self.density = density self.latent_size = latent_size self.initial_size = initial_size
def __init__(self, density=1, size=64, latent_size=100, channel=3): assert (size % 16 == 0) initial_size = size / 16 super(Generator_origin, self).__init__( g1=L.Linear(latent_size, initial_size * initial_size * 256 * density, wscale=0.02 * math.sqrt(latent_size)), norm1=L.BatchNormalization(initial_size * initial_size * 256 * density), g2=L.Deconvolution2D(256 * density, 128 * density, 4, stride=2, pad=1, wscale=0.02 * math.sqrt(4 * 4 * 256 * density)), norm2=L.BatchNormalization(128 * density), g3=L.Deconvolution2D(128 * density, 64 * density, 4, stride=2, pad=1, wscale=0.02 * math.sqrt(4 * 4 * 128 * density)), norm3=L.BatchNormalization(64 * density), g4=L.Deconvolution2D(64 * density, 32 * density, 4, stride=2, pad=1, wscale=0.02 * math.sqrt(4 * 4 * 64 * density)), norm4=L.BatchNormalization(32 * density), g5=L.Deconvolution2D(32 * density, channel, 4, stride=2, pad=1, wscale=0.02 * math.sqrt(4 * 4 * 32 * density)), ) self.density = density self.latent_size = latent_size self.initial_size = initial_size
def __init__(self, ch0, ch1, bn=True, sample='down', activation=F.relu, dropout=False, noise=False): self.bn = bn self.activation = activation self.dropout = dropout self.noise = noise layers = {} w = chainer.initializers.Normal(0.02) if sample == 'down': layers['c'] = L.Convolution2D(ch0, ch1, 4, 2, 1, initialW=w) elif sample == 'up': layers['c'] = L.Deconvolution2D(ch0, ch1, 4, 2, 1, initialW=w) elif sample == 'c7s1': layers['c'] = L.Convolution2D(ch0, ch1, 7, 1, 3, initialW=w) if bn: if self.noise: layers['batchnorm'] = L.BatchNormalization(ch1, use_gamma=False) else: layers['batchnorm'] = L.BatchNormalization(ch1) super(CBR, self).__init__(**layers)
def __init__(self, ch=128, wscale=0.02): w = chainer.initializers.Normal(wscale) super(GeneratorOld, self).__init__( conv1=L.Convolution2D(3, ch // 4, 5, 1, 2, initialW=w), conv2=L.Convolution2D(ch // 4, ch // 2, 3, 2, 1, initialW=w), conv3=L.Convolution2D(ch // 2, ch, 3, 2, 1, initialW=w), res1=ResBlock(ch, ch, bn=False), res2=ResBlock(ch, ch, bn=False), res3=ResBlock(ch, ch, bn=False), res4=ResBlock(ch, ch, bn=False), res5=ResBlock(ch, ch, bn=False), res6=ResBlock(ch, ch, bn=False), res7=ResBlock(ch, ch, bn=False), res8=ResBlock(ch, ch, bn=False), res9=ResBlock(ch, ch, bn=False), dc1=L.Deconvolution2D(ch, ch // 2, 4, 2, 1, initialW=w), dc2=L.Deconvolution2D(ch // 2, ch // 4, 4, 2, 1, initialW=w), dc3=L.Convolution2D(ch // 4, 3, 5, 1, 2, initialW=w), ) # noinspection PyCallingNonCallable,PyUnresolvedReferences
def __init__(self, n_class=21): self.train=True super(FCN32s, self).__init__( conv1_1=L.Convolution2D(3, 64, 3, stride=1, pad=100), conv1_2=L.Convolution2D(64, 64, 3, stride=1, pad=1), conv2_1=L.Convolution2D(64, 128, 3, stride=1, pad=1), conv2_2=L.Convolution2D(128, 128, 3, stride=1, pad=1), conv3_1=L.Convolution2D(128, 256, 3, stride=1, pad=1), conv3_2=L.Convolution2D(256, 256, 3, stride=1, pad=1), conv3_3=L.Convolution2D(256, 256, 3, stride=1, pad=1), conv4_1=L.Convolution2D(256, 512, 3, stride=1, pad=1), conv4_2=L.Convolution2D(512, 512, 3, stride=1, pad=1), conv4_3=L.Convolution2D(512, 512, 3, stride=1, pad=1), conv5_1=L.Convolution2D(512, 512, 3, stride=1, pad=1), conv5_2=L.Convolution2D(512, 512, 3, stride=1, pad=1), conv5_3=L.Convolution2D(512, 512, 3, stride=1, pad=1), fc6=L.Convolution2D(512, 4096, 7, stride=1, pad=0), fc7=L.Convolution2D(4096, 4096, 1, stride=1, pad=0), score_fr=L.Convolution2D(4096, n_class, 1, stride=1, pad=0, nobias=True, initialW=np.zeros((n_class, 4096, 1, 1))), upscore=L.Deconvolution2D(n_class, n_class, 64, stride=32, pad=0, nobias=True, initialW=f.bilinear_interpolation_kernel(n_class, n_class, ksize=64)), )
def check_add_deconv_layers(self, nobias=True): """Add a deconvolutional layer for each convolutional layer already defined in the network.""" if len(self.deconv_blocks) == len(self.conv_blocks): return for conv_block in self.conv_blocks: deconv_block = [] for conv in conv_block: out_channels, in_channels, kh, kw = conv.W.data.shape if isinstance(conv.W.data, cuda.ndarray): initialW = cuda.cupy.asnumpy(conv.W.data) else: initialW = conv.W.data deconv = L.Deconvolution2D(out_channels, in_channels, (kh, kw), stride=conv.stride, pad=conv.pad, initialW=initialW, nobias=nobias) if isinstance(conv.W.data, cuda.ndarray): deconv.to_gpu() self.add_link('de{}'.format(conv.name), deconv) deconv_block.append(deconv) self.deconv_blocks.append(deconv_block)
def __init__(self, n_class=21): self.n_class = n_class kwargs = { 'initialW': chainer.initializers.Zero(), 'initial_bias': chainer.initializers.Zero(), } super(FCN16s, self).__init__() with self.init_scope(): self.conv1_1 = L.Convolution2D(3, 64, 3, 1, 100, **kwargs) self.conv1_2 = L.Convolution2D(64, 64, 3, 1, 1, **kwargs) self.conv2_1 = L.Convolution2D(64, 128, 3, 1, 1, **kwargs) self.conv2_2 = L.Convolution2D(128, 128, 3, 1, 1, **kwargs) self.conv3_1 = L.Convolution2D(128, 256, 3, 1, 1, **kwargs) self.conv3_2 = L.Convolution2D(256, 256, 3, 1, 1, **kwargs) self.conv3_3 = L.Convolution2D(256, 256, 3, 1, 1, **kwargs) self.conv4_1 = L.Convolution2D(256, 512, 3, 1, 1, **kwargs) self.conv4_2 = L.Convolution2D(512, 512, 3, 1, 1, **kwargs) self.conv4_3 = L.Convolution2D(512, 512, 3, 1, 1, **kwargs) self.conv5_1 = L.Convolution2D(512, 512, 3, 1, 1, **kwargs) self.conv5_2 = L.Convolution2D(512, 512, 3, 1, 1, **kwargs) self.conv5_3 = L.Convolution2D(512, 512, 3, 1, 1, **kwargs) self.fc6 = L.Convolution2D(512, 4096, 7, 1, 0, **kwargs) self.fc7 = L.Convolution2D(4096, 4096, 1, 1, 0, **kwargs) self.score_fr = L.Convolution2D(4096, n_class, 1, 1, 0, **kwargs) self.score_pool4 = L.Convolution2D(512, n_class, 1, 1, 0, **kwargs) self.upscore2 = L.Deconvolution2D( n_class, n_class, 4, 2, nobias=True, initialW=initializers.UpsamplingDeconvWeight()) self.upscore16 = L.Deconvolution2D( n_class, n_class, 32, 16, nobias=True, initialW=initializers.UpsamplingDeconvWeight())
def __init__(self, n_class=21): self.n_class = n_class kwargs = { 'initialW': chainer.initializers.Zero(), 'initial_bias': chainer.initializers.Zero(), } super(FCN32s, self).__init__() with self.init_scope(): self.conv1_1 = L.Convolution2D(3, 64, 3, 1, 100, **kwargs) self.conv1_2 = L.Convolution2D(64, 64, 3, 1, 1, **kwargs) self.conv2_1 = L.Convolution2D(64, 128, 3, 1, 1, **kwargs) self.conv2_2 = L.Convolution2D(128, 128, 3, 1, 1, **kwargs) self.conv3_1 = L.Convolution2D(128, 256, 3, 1, 1, **kwargs) self.conv3_2 = L.Convolution2D(256, 256, 3, 1, 1, **kwargs) self.conv3_3 = L.Convolution2D(256, 256, 3, 1, 1, **kwargs) self.conv4_1 = L.Convolution2D(256, 512, 3, 1, 1, **kwargs) self.conv4_2 = L.Convolution2D(512, 512, 3, 1, 1, **kwargs) self.conv4_3 = L.Convolution2D(512, 512, 3, 1, 1, **kwargs) self.conv5_1 = L.Convolution2D(512, 512, 3, 1, 1, **kwargs) self.conv5_2 = L.Convolution2D(512, 512, 3, 1, 1, **kwargs) self.conv5_3 = L.Convolution2D(512, 512, 3, 1, 1, **kwargs) self.fc6 = L.Convolution2D(512, 4096, 7, 1, 0, **kwargs) self.fc7 = L.Convolution2D(4096, 4096, 1, 1, 0, **kwargs) self.score_fr = L.Convolution2D(4096, n_class, 1, 1, 0, **kwargs) self.upscore = L.Deconvolution2D( n_class, n_class, 64, 32, 0, nobias=True, initialW=initializers.UpsamplingDeconvWeight())
def __init__(self): initialW = chainer.initializers.Normal(0.02) super(Generator1, self).__init__( conv1=L.Deconvolution2D(100, 1024, 4, initialW=initialW), bn1=L.BatchNormalization(1024), up=UpSampling(4, 1024, 64), )
def __init__(self): super(MyFcn, self).__init__( conv1_1=L.Convolution2D( 3, 64, 3, stride=1, pad=1), conv1_2=L.Convolution2D( 64, 64, 3, stride=1, pad=1), conv2_1=L.Convolution2D( 64, 128, 3, stride=1, pad=1), conv2_2=L.Convolution2D(128, 128, 3, stride=1, pad=1), conv3_1=L.Convolution2D(128, 256, 3, stride=1, pad=1), conv3_2=L.Convolution2D(256, 256, 3, stride=1, pad=1), conv3_3=L.Convolution2D(256, 256, 3, stride=1, pad=1), conv4_1=L.Convolution2D(256, 512, 3, stride=1, pad=1), conv4_2=L.Convolution2D(512, 512, 3, stride=1, pad=1), conv4_3=L.Convolution2D(512, 512, 3, stride=1, pad=1), conv5_1=L.Convolution2D(512, 512, 3, stride=1, pad=1), conv5_2=L.Convolution2D(512, 512, 3, stride=1, pad=1), conv5_3=L.Convolution2D(512, 512, 3, stride=1, pad=1), score_pool3=L.Convolution2D(256, MyFcn.CLASSES, 1, stride=1, pad=0), score_pool4=L.Convolution2D(512, MyFcn.CLASSES, 1, stride=1, pad=0), score_pool5=L.Convolution2D(512, MyFcn.CLASSES, 1, stride=1, pad=0), upsample_pool4=L.Deconvolution2D(MyFcn.CLASSES, MyFcn.CLASSES, ksize= 4, stride=2, pad=1), upsample_pool5=L.Deconvolution2D(MyFcn.CLASSES, MyFcn.CLASSES, ksize= 8, stride=4, pad=2), upsample_final=L.Deconvolution2D(MyFcn.CLASSES, MyFcn.CLASSES, ksize=16, stride=8, pad=4), ) self.train = True
def __init__(self): super().__init__( dc1=L.Deconvolution2D(None, 256, 4, stride=1, pad=0, nobias=True), dc2=L.Deconvolution2D(256, 128, 4, stride=2, pad=1, nobias=True), dc3=L.Deconvolution2D(128, 64, 4, stride=2, pad=1, nobias=True), dc4=L.Deconvolution2D(64, 3, 4, stride=2, pad=1, nobias=True), bn_dc1=L.BatchNormalization(256), bn_dc2=L.BatchNormalization(128), bn_dc3=L.BatchNormalization(64) )
def __init__(self, size=None): super().__init__( dc1=L.Deconvolution2D(None, 256, 4, stride=1, pad=0, nobias=True), dc2=L.Deconvolution2D(256, 128, 4, stride=2, pad=1, nobias=True), dc3=L.Deconvolution2D(128, 64, 4, stride=2, pad=1, nobias=True), dc4=L.Deconvolution2D(64, 3, 4, stride=2, pad=1, nobias=True), bn_dc1=L.BatchNormalization(256), bn_dc2=L.BatchNormalization(128), bn_dc3=L.BatchNormalization(64) )
def __init__(self, size=None): super().__init__( dc1=L.Deconvolution2D(None, 256, 4, stride=1, pad=0, nobias=True), dc2=L.Deconvolution2D(256, 128, 4, stride=2, pad=1, nobias=True), dc3=L.Deconvolution2D(128, 64, 4, stride=2, pad=2, nobias=True), dc4=L.Deconvolution2D(64, 1, 4, stride=2, pad=1, nobias=True), bn_dc1=L.BatchNormalization(256), bn_dc2=L.BatchNormalization(128), bn_dc3=L.BatchNormalization(64) )
def __init__(self, feature_map_nc, output_nc, w_init=None): super(Generator, self).__init__( c1=L.Convolution2D(None, feature_map_nc, ksize=4, stride=2, pad=1, initialW=w_init), c2=L.Convolution2D(None, 2*feature_map_nc, ksize=4, stride=2, pad=1, initialW=w_init), c3=L.Convolution2D(None, 4*feature_map_nc, ksize=4, stride=2, pad=1, initialW=w_init), c4=L.Convolution2D(None, 8*feature_map_nc, ksize=4, stride=2, pad=1, initialW=w_init), c5=L.Convolution2D(None, 8*feature_map_nc, ksize=4, stride=2, pad=1, initialW=w_init), c6=L.Convolution2D(None, 8*feature_map_nc, ksize=4, stride=2, pad=1, initialW=w_init), c7=L.Convolution2D(None, 8*feature_map_nc, ksize=4, stride=2, pad=1, initialW=w_init), c8=L.Convolution2D(None, 8*feature_map_nc, ksize=4, stride=2, pad=1, initialW=w_init), dc1=L.Deconvolution2D(None, 8*feature_map_nc, ksize=4, stride=2, pad=1, initialW=w_init), dc2=L.Deconvolution2D(None, 8*feature_map_nc, ksize=4, stride=2, pad=1, initialW=w_init), dc3=L.Deconvolution2D(None, 8*feature_map_nc, ksize=4, stride=2, pad=1, initialW=w_init), dc4=L.Deconvolution2D(None, 8*feature_map_nc, ksize=4, stride=2, pad=1, initialW=w_init), dc5=L.Deconvolution2D(None, 4*feature_map_nc, ksize=4, stride=2, pad=1, initialW=w_init), dc6=L.Deconvolution2D(None, 2*feature_map_nc, ksize=4, stride=2, pad=1, initialW=w_init), dc7=L.Deconvolution2D(None, feature_map_nc, ksize=4, stride=2, pad=1, initialW=w_init), dc8=L.Deconvolution2D(None, output_nc, ksize=4, stride=2, pad=1, initialW=w_init), b2=L.BatchNormalization(2*feature_map_nc), b3=L.BatchNormalization(4*feature_map_nc), b4=L.BatchNormalization(8*feature_map_nc), b5=L.BatchNormalization(8*feature_map_nc), b6=L.BatchNormalization(8*feature_map_nc), b7=L.BatchNormalization(8*feature_map_nc), b8=L.BatchNormalization(8*feature_map_nc), b1_d=L.BatchNormalization(8*feature_map_nc), b2_d=L.BatchNormalization(8*feature_map_nc), b3_d=L.BatchNormalization(8*feature_map_nc), b4_d=L.BatchNormalization(8*feature_map_nc), b5_d=L.BatchNormalization(4*feature_map_nc), b6_d=L.BatchNormalization(2*feature_map_nc), b7_d=L.BatchNormalization(feature_map_nc) )
def __init__(self, ch0, ch1, bn=True, sample='down', activation=F.relu, dropout=False): self.bn = bn self.activation = activation self.dropout = dropout layers = {} w = chainer.initializers.Normal(0.02) if sample=='down': layers['c'] = L.Convolution2D(ch0, ch1, 4, 2, 1, initialW=w) else: layers['c'] = L.Deconvolution2D(ch0, ch1, 4, 2, 1, initialW=w) if bn: layers['batchnorm'] = L.BatchNormalization(ch1) super(CBR, self).__init__(**layers)
def __init__(self, nz=30): super(Generator, self).__init__( l0z=L.Linear(nz, 6 * 6 * 128, wscale=0.02 * math.sqrt(nz)), dc1=L.Deconvolution2D(128, 64, 4, stride=2, pad=1, wscale=0.02 * math.sqrt(4 * 4 * 128)), dc2=L.Deconvolution2D(64, 32, 4, stride=2, pad=1, wscale=0.02 * math.sqrt(4 * 4 * 64)), dc3=L.Deconvolution2D(32, 1, 4, stride=2, pad=1, wscale=0.02 * math.sqrt(4 * 4 * 32)), bn0l=L.BatchNormalization(6 * 6 * 128), bn0=L.BatchNormalization(128), bn1=L.BatchNormalization(64), bn2=L.BatchNormalization(32) )
def __init__(self, ch=512, wscale=0.02): w = chainer.initializers.Normal(wscale) self.ch = ch super(Discriminator, self).__init__() with self.init_scope(): self.c0 = L.Convolution2D(3, ch // 8, 3, 1, 1, initialW=w) self.c1 = L.Convolution2D(ch // 8, ch // 4, 4, 2, 1, initialW=w) self.c2 = L.Convolution2D(ch // 4, ch // 2, 4, 2, 1, initialW=w) self.c3 = L.Convolution2D(ch // 2, ch // 1, 4, 2, 1, initialW=w) self.l4 = L.Linear(4*4*ch, 128, initialW=w) self.l5 = L.Linear(128, 4*4*ch, initialW=w) self.dc3 = L.Deconvolution2D(ch // 1, ch // 2, 4, 2, 1, initialW=w) self.dc2 = L.Deconvolution2D(ch // 2, ch // 4, 4, 2, 1, initialW=w) self.dc1 = L.Deconvolution2D(ch // 4, ch // 8, 4, 2, 1, initialW=w) self.dc0 = L.Deconvolution2D(ch // 8, 3, 3, 1, 1, initialW=w)
def __init__(self, z_dim): super(Generator, self).__init__( l1=L.Deconvolution2D(z_dim, 128, 3, 2, 0), bn1=L.BatchNormalization(128), l2=L.Deconvolution2D(128, 128, 3, 2, 1), bn2=L.BatchNormalization(128), l3=L.Deconvolution2D(128, 128, 3, 2, 1), bn3=L.BatchNormalization(128), l4=L.Deconvolution2D(128, 128, 3, 2, 2), bn4=L.BatchNormalization(128), l5=L.Deconvolution2D(128, 1, 3, 2, 2, outsize=(28, 28)), ) self.train = True
def __init__(self, ch0, ch1, bn=True, sample='down', activation=F.relu, dropout=False): self.bn = bn self.activation = activation self.dropout = dropout layers = {} w = chainer.initializers.Normal(0.02) if sample == 'down': layers['c'] = L.Convolution2D(ch0, ch1, 4, 2, 1, initialW=w) else: layers['c'] = L.Deconvolution2D(ch0, ch1, 4, 2, 1, initialW=w) if bn: layers['batchnorm'] = L.BatchNormalization(ch1) super(CBR, self).__init__(**layers)
def __init__(self): super(COLORNet, self).__init__( fx0=L.Linear(1000, 512), fx1=L.Linear(512, 256), convf_0=L.Convolution2D(512, 256, 1, stride=1, pad=0), bn0 = L.BatchNormalization(512), conv5_1=L.Convolution2D(512, 512, 1, stride=1, pad=0), deconv5_1 = L.Deconvolution2D(512, 512, 2, stride=2, pad=0), conv4_1=L.Convolution2D(512, 256, 1, stride=1, pad=0), bn1 = L.BatchNormalization(512), deconv4_1 = L.Deconvolution2D(256, 256, 2, stride=2, pad=0), bn2 = L.BatchNormalization(256), conv4_2=L.Convolution2D(256, 128, 3, stride=1, pad=1), bn3 = L.BatchNormalization(128), deconv3_1 = L.Deconvolution2D(128, 128, 2, stride=2, pad=0), bn4 = L.BatchNormalization(128), conv3_1=L.Convolution2D(128, 64, 3, stride=1, pad=1), bn5 = L.BatchNormalization(64), deconv2_1 = L.Deconvolution2D(64, 64, 2, stride=2, pad=0), bn6 = L.BatchNormalization(64), conv2_1=L.Convolution2D(64, 3, 3, stride=1, pad=1), bn7 = L.BatchNormalization(3), bn8 = L.BatchNormalization(3), conv1_1=L.Convolution2D(3, 3, 3, stride=1, pad=1), bn9 = L.BatchNormalization(3), conv0_5=L.Convolution2D(3, 2, 3, stride=1, pad=1), )
def __init__(self, n_class=21): self.train=True super(FCN16s, self).__init__( conv1_1=L.Convolution2D(3, 64, 3, stride=1, pad=100), conv1_2=L.Convolution2D(64, 64, 3, stride=1, pad=1), conv2_1=L.Convolution2D(64, 128, 3, stride=1, pad=1), conv2_2=L.Convolution2D(128, 128, 3, stride=1, pad=1), conv3_1=L.Convolution2D(128, 256, 3, stride=1, pad=1), conv3_2=L.Convolution2D(256, 256, 3, stride=1, pad=1), conv3_3=L.Convolution2D(256, 256, 3, stride=1, pad=1), conv4_1=L.Convolution2D(256, 512, 3, stride=1, pad=1), conv4_2=L.Convolution2D(512, 512, 3, stride=1, pad=1), conv4_3=L.Convolution2D(512, 512, 3, stride=1, pad=1), conv5_1=L.Convolution2D(512, 512, 3, stride=1, pad=1), conv5_2=L.Convolution2D(512, 512, 3, stride=1, pad=1), conv5_3=L.Convolution2D(512, 512, 3, stride=1, pad=1), fc6=L.Convolution2D(512, 4096, 7, stride=1, pad=0), fc7=L.Convolution2D(4096, 4096, 1, stride=1, pad=0), score_fr=L.Convolution2D(4096, n_class, 1, stride=1, pad=0, nobias=True, initialW=np.zeros((n_class, 4096, 1, 1))), score_pool4=L.Convolution2D(512, n_class, 1, stride=1, pad=0, nobias=True, initialW=np.zeros((n_class, 512, 1, 1))), upscore2=L.Deconvolution2D(n_class, n_class, 4, stride=2, nobias=True, initialW=f.bilinear_interpolation_kernel(n_class, n_class, ksize=4), use_cudnn=False), upscore16=L.Deconvolution2D(n_class, n_class, 32, stride=16, nobias=True, initialW=f.bilinear_interpolation_kernel(n_class, n_class, ksize=32), use_cudnn=False), )
def __init__(self, n_class=21): self.train = True super(FCN8s, self).__init__( conv1_1=L.Convolution2D(3, 64, 3, stride=1, pad=100), conv1_2=L.Convolution2D(64, 64, 3, stride=1, pad=1), conv2_1=L.Convolution2D(64, 128, 3, stride=1, pad=1), conv2_2=L.Convolution2D(128, 128, 3, stride=1, pad=1), conv3_1=L.Convolution2D(128, 256, 3, stride=1, pad=1), conv3_2=L.Convolution2D(256, 256, 3, stride=1, pad=1), conv3_3=L.Convolution2D(256, 256, 3, stride=1, pad=1), conv4_1=L.Convolution2D(256, 512, 3, stride=1, pad=1), conv4_2=L.Convolution2D(512, 512, 3, stride=1, pad=1), conv4_3=L.Convolution2D(512, 512, 3, stride=1, pad=1), conv5_1=L.Convolution2D(512, 512, 3, stride=1, pad=1), conv5_2=L.Convolution2D(512, 512, 3, stride=1, pad=1), conv5_3=L.Convolution2D(512, 512, 3, stride=1, pad=1), fc6=L.Convolution2D(512, 4096, 7, stride=1, pad=0), fc7=L.Convolution2D(4096, 4096, 1, stride=1, pad=0), score_fr=L.Convolution2D(4096, n_class, 1, stride=1, pad=0, nobias=True, initialW=np.zeros((n_class, 4096, 1, 1))), score_pool3=L.Convolution2D(256, n_class, 1, stride=1, pad=0, nobias=True, initialW=np.zeros((n_class, 256, 1, 1))), score_pool4=L.Convolution2D(512, n_class, 1, stride=1, pad=0, nobias=True, initialW=np.zeros((n_class, 512, 1, 1))), upscore2=L.Deconvolution2D(n_class, n_class, 4, stride=2, nobias=True, initialW=f.bilinear_interpolation_kernel(n_class, n_class, ksize=4), use_cudnn=False), upscore_pool4=L.Deconvolution2D(n_class, n_class, 4, stride=2, nobias=True, initialW=f.bilinear_interpolation_kernel(n_class, n_class, ksize=4), use_cudnn=False), upscore8=L.Deconvolution2D(n_class, n_class, 16, stride=8, nobias=True, initialW=f.bilinear_interpolation_kernel(n_class, n_class, ksize=16), use_cudnn=False), )
def __init__(self, n_z, out_shape): super(Generator, self).__init__( fc0=L.Linear(n_z, lindim(out_shape, 2**4, 256)), dc1=L.Deconvolution2D(256, 128, 4, stride=2, pad=1), dc2=L.Deconvolution2D(128, 64, 4, stride=2, pad=1), dc3=L.Deconvolution2D(64, 32, 4, stride=2, pad=1), dc4=L.Deconvolution2D(32, 1, 4, stride=2, pad=1), bn0=L.BatchNormalization(lindim(out_shape, 2**4, 256)), bn1=L.BatchNormalization(128), bn2=L.BatchNormalization(64), bn3=L.BatchNormalization(32) ) self.out_shape = out_shape
def __init__(self): initializer = initializers.HeNormal() super(Generator, self).__init__( # num of noise that becomes the seed of Generation is 100 l0z = L.Linear(100, 7*7*128, initialW = initializer), dc1 = L.Deconvolution2D(128, 64, 4, stride=2, pad=1, initialW = initializer), dc2 = L.Deconvolution2D(64, 1, 4, stride=2, pad=1, initialW = initializer), bn0 = L.BatchNormalization(7*7*128), bn1 = L.BatchNormalization(64), )
def __init__(self): initializer = initializers.HeNormal() super(Generator, self).__init__( l0z = L.Linear(100, 7*7*128, initialW = initializer), dc1 = L.Deconvolution2D(128, 64, 4, stride=2, pad=1, initialW = initializer), dc2 = L.Deconvolution2D(64, 1, 4, stride=2, pad=1, initialW = initializer), bn0 = L.BatchNormalization(7*7*128), bn1 = L.BatchNormalization(64), )
def __init__(self): initializer = initializers.HeNormal() super(Generator, self).__init__( l0z = L.Linear(100+10, 7*7*128, initialW = initializer), dc1 = L.Deconvolution2D(128, 64, 4, stride=2, pad=1, initialW = initializer), dc2 = L.Deconvolution2D(64, 1, 4, stride=2, pad=1, initialW = initializer), bn0 = L.BatchNormalization(7*7*128), bn1 = L.BatchNormalization(64), )
def __init__(self): super(AutoENC, self).__init__( c0=L.Convolution2D(None, 32, 3, 1, 1), c1=L.Convolution2D(32, 64, 4, 2, 1), c2=L.Convolution2D(64, 128, 4, 2, 1), c3=L.Convolution2D(128, 256, 4, 2, 1), c4=L.Convolution2D(256, 512, 4, 2, 1), c5=L.Convolution2D(512, 512, 3, 1, 1), dc5=L.Deconvolution2D(512, 512, 4, 2, 1), dc4=L.Deconvolution2D(512, 256, 4, 2, 1), dc3=L.Deconvolution2D(256, 128, 4, 2, 1), dc2=L.Deconvolution2D(128, 64, 4, 2, 1), dc1=L.Convolution2D(64, 32, 3, 1, 1), dc0=L.Convolution2D(32, 3, 3, 1, 1), bnc0=L.BatchNormalization(32), bnc1=L.BatchNormalization(64), bnc2=L.BatchNormalization(128), bnc3=L.BatchNormalization(256), bnc4=L.BatchNormalization(512), bnc5=L.BatchNormalization(512), bnd5=L.BatchNormalization(512), bnd4=L.BatchNormalization(256), bnd3=L.BatchNormalization(128), bnd2=L.BatchNormalization(64), bnd1=L.BatchNormalization(32) )
def __init__(self, ch0, ch1, \ nn='conv', \ norm='bn', \ activation=F.relu, \ dropout=False, \ noise=None, \ w_init=None, \ k_size = 3, \ normalize_input=False ): self.norm = norm self.normalize_input = normalize_input self.activation = activation self.dropout = dropout self.noise = noise self.nn = nn layers = {} if w_init == None: w = chainer.initializers.GlorotNormal() else: w = w_init if nn == 'down_conv': layers['c'] = L.Convolution2D(ch0, ch1, 4, 2, 1, initialW=w) elif nn == 'up_deconv': layers['c'] = L.Deconvolution2D(ch0, ch1, 4, 2, 1, initialW=w) elif nn == 'up_subpixel': pad = k_size//2 layers['c'] = L.Convolution2D(ch0, ch1*4, k_size, 1, pad, initialW=w) elif nn=='conv' or nn=='up_unpooling': pad = k_size//2 layers['c'] = L.Convolution2D(ch0, ch1, k_size, 1, pad, initialW=w) elif nn=='linear': layers['c'] = L.Linear(ch0, ch1, initialW=w) else: raise Exception("Cannot find method %s" % nn) if self.norm == 'bn': if self.noise: layers['n'] = L.BatchNormalization(ch1, use_gamma=False) else: layers['n'] = L.BatchNormalization(ch1) elif self.norm == 'ln': layers['n'] = L.LayerNormalization(ch1) super(NNBlock, self).__init__(**layers)
def __init__(self, n_class=21): self.n_class = n_class kwargs = { 'initialW': chainer.initializers.Zero(), 'initial_bias': chainer.initializers.Zero(), } super(FCN8s, self).__init__() with self.init_scope(): self.conv1_1 = L.Convolution2D(3, 64, 3, 1, 100, **kwargs) self.conv1_2 = L.Convolution2D(64, 64, 3, 1, 1, **kwargs) self.conv2_1 = L.Convolution2D(64, 128, 3, 1, 1, **kwargs) self.conv2_2 = L.Convolution2D(128, 128, 3, 1, 1, **kwargs) self.conv3_1 = L.Convolution2D(128, 256, 3, 1, 1, **kwargs) self.conv3_2 = L.Convolution2D(256, 256, 3, 1, 1, **kwargs) self.conv3_3 = L.Convolution2D(256, 256, 3, 1, 1, **kwargs) self.conv4_1 = L.Convolution2D(256, 512, 3, 1, 1, **kwargs) self.conv4_2 = L.Convolution2D(512, 512, 3, 1, 1, **kwargs) self.conv4_3 = L.Convolution2D(512, 512, 3, 1, 1, **kwargs) self.conv5_1 = L.Convolution2D(512, 512, 3, 1, 1, **kwargs) self.conv5_2 = L.Convolution2D(512, 512, 3, 1, 1, **kwargs) self.conv5_3 = L.Convolution2D(512, 512, 3, 1, 1, **kwargs) self.fc6 = L.Convolution2D(512, 4096, 7, 1, 0, **kwargs) self.fc7 = L.Convolution2D(4096, 4096, 1, 1, 0, **kwargs) self.score_fr = L.Convolution2D(4096, n_class, 1, 1, 0, **kwargs) self.upscore2 = L.Deconvolution2D( n_class, n_class, 4, 2, 0, nobias=True, initialW=initializers.UpsamplingDeconvWeight()) self.upscore8 = L.Deconvolution2D( n_class, n_class, 16, 8, 0, nobias=True, initialW=initializers.UpsamplingDeconvWeight()) self.score_pool3 = L.Convolution2D(256, n_class, 1, 1, 0, **kwargs) self.score_pool4 = L.Convolution2D(512, n_class, 1, 1, 0, **kwargs) self.upscore_pool4 = L.Deconvolution2D( n_class, n_class, 4, 2, 0, nobias=True, initialW=initializers.UpsamplingDeconvWeight())
def __init__(self, name, CLASSES, preNet=None): super(FCN, self).__init__( # params of the model #ipdb.set_trace(), conv1_1 = L.Convolution2D(3, 64, 3, stride=(1, 1), pad=(1, 1), initialW=None, initial_bias=None), conv1_2 = L.Convolution2D(64, 64, 3, stride=(1, 1), pad=(1, 1), initialW=None, initial_bias=None), conv2_1 = L.Convolution2D(64, 128, 3, stride=(1, 1), pad=(1, 1), initialW=None, initial_bias=None), conv2_2 = L.Convolution2D(128, 128, 3, stride=(1, 1), pad=(1, 1), initialW=None, initial_bias=None), conv3_1 = L.Convolution2D(128, 256, 3, stride=(1, 1), pad=(1, 1), initialW=None, initial_bias=None), conv3_2 = L.Convolution2D(256, 256, 3, stride=(1, 1), pad=(1, 1), initialW=None, initial_bias=None), conv3_3 = L.Convolution2D(256, 256, 3, stride=(1, 1), pad=(1, 1), initialW=None, initial_bias=None), conv4_1 = L.Convolution2D(256, 512, 3, stride=(1, 1), pad=(1, 1), initialW=None, initial_bias=None), conv4_2 = L.Convolution2D(512, 512, 3, stride=(1, 1), pad=(1, 1), initialW=None, initial_bias=None), conv4_3 = L.Convolution2D(512, 512, 3, stride=(1, 1), pad=(1, 1), initialW=None, initial_bias=None), conv5_1 = L.Convolution2D(512, 512, 3, stride=(1, 1), pad=(1, 1), initialW=None, initial_bias=None), conv5_2 = L.Convolution2D(512, 512, 3, stride=(1, 1), pad=(1, 1), initialW=None, initial_bias=None), conv5_3 = L.Convolution2D(512, 512, 3, stride=(1, 1), pad=(1, 1), initialW=None, initial_bias=None), #conv_aux = L.Convolution2D(512, 512, (7, 6), stride=(1, 1), pad=(0, 1), initialW=None, initial_bias=None), #conv_auxb = L.Convolution2D(512, 512, (7, 7), stride=(1, 1), pad=(0, 0), initialW=None, initial_bias=None), fc_6 = L.Convolution2D(512, 4096, 1, stride=(1, 1), pad=(0, 0), initialW=None, initial_bias=None), fc_7 = L.Convolution2D(4096, 4096, 1, stride=(1, 1), pad=(0, 0), initialW=None, initial_bias=None), #fc_6 = L.Linear(512, 4096, wscale=1, bias=0, nobias=False, initialW=None, initial_bias=None), #fc_7 = L.Linear(4096, 4096, wscale=1, bias=0, nobias=False, initialW=None, initial_bias=None), conv_aux2 = L.Convolution2D(4096, CLASSES, 1, stride=(1, 1), pad=(0, 0), initialW=None, initial_bias=None), score2 = L.Deconvolution2D(CLASSES, CLASSES, (4,5), stride=(2, 2), pad=(1, 2)), score_pool4 = L.Convolution2D(512, CLASSES, 1, stride=(1, 1), pad=(0, 0), initialW=None, initial_bias=None), score4 = L.Deconvolution2D(CLASSES, CLASSES, (4,3), stride=(2, 2), pad=(1, 1)), score_pool3 = L.Convolution2D(256, CLASSES, 1, stride=(1, 1), pad=(0, 0), initialW=None, initial_bias=None), upsample = L.Deconvolution2D(CLASSES, CLASSES, 8, stride=(8, 8), pad=(0, 0)), classi = L.Convolution2D(CLASSES, CLASSES, 1, stride=(1, 1), pad=(0, 0), initialW=None, initial_bias=None), ), self.name = name self.classes = CLASSES
def __init__(self, name, CLASSES, preNet=None): super(FCN_BND, self).__init__( # params of the model #ipdb.set_trace(), conv1_1 = L.Convolution2D(3, 64, 3, stride=(1, 1), pad=(1, 1), initialW=None, initial_bias=None), bn1_1 = L.BatchNormalization(64), conv1_2 = L.Convolution2D(64, 64, 3, stride=(1, 1), pad=(1, 1), initialW=None, initial_bias=None), bn1_2 = L.BatchNormalization(64), conv2_1 = L.Convolution2D(64, 128, 3, stride=(1, 1), pad=(1, 1), initialW=None, initial_bias=None), bn2_1 = L.BatchNormalization(128), conv2_2 = L.Convolution2D(128, 128, 3, stride=(1, 1), pad=(1, 1), initialW=None, initial_bias=None), bn2_2 = L.BatchNormalization(128), conv3_1 = L.Convolution2D(128, 256, 3, stride=(1, 1), pad=(1, 1), initialW=None, initial_bias=None), bn3_1 = L.BatchNormalization(256), conv3_2 = L.Convolution2D(256, 256, 3, stride=(1, 1), pad=(1, 1), initialW=None, initial_bias=None), bn3_2 = L.BatchNormalization(256), conv3_3 = L.Convolution2D(256, 256, 3, stride=(1, 1), pad=(1, 1), initialW=None, initial_bias=None), bn3_3 = L.BatchNormalization(256), conv4_1 = L.Convolution2D(256, 512, 3, stride=(1, 1), pad=(1, 1), initialW=None, initial_bias=None), bn4_1 = L.BatchNormalization(512), conv4_2 = L.Convolution2D(512, 512, 3, stride=(1, 1), pad=(1, 1), initialW=None, initial_bias=None), bn4_2 = L.BatchNormalization(512), conv4_3 = L.Convolution2D(512, 512, 3, stride=(1, 1), pad=(1, 1), initialW=None, initial_bias=None), bn4_3 = L.BatchNormalization(512), conv5_1 = L.Convolution2D(512, 512, 3, stride=(1, 1), pad=(1, 1), initialW=None, initial_bias=None), bn5_1 = L.BatchNormalization(512), conv5_2 = L.Convolution2D(512, 512, 3, stride=(1, 1), pad=(1, 1), initialW=None, initial_bias=None), bn5_2 = L.BatchNormalization(512), conv5_3 = L.Convolution2D(512, 512, 3, stride=(1, 1), pad=(1, 1), initialW=None, initial_bias=None), bn5_3 = L.BatchNormalization(512), fc6 = L.Convolution2D(512, 4096, 7, stride=(1, 1), pad=(3, 3), initialW=None, initial_bias=None), fc7 = L.Convolution2D(4096, 4096, 1, stride=(1, 1), pad=(0, 0), initialW=None, initial_bias=None), score_fr = L.Convolution2D(4096, CLASSES, 1, stride=(1, 1), pad=(0, 0), initialW=None, initial_bias=None), score2 = L.Deconvolution2D(CLASSES, CLASSES, (4,3), stride=(2, 2), pad=(1, 1), initialW=None, initial_bias=None), score_pool4 = L.Convolution2D(512, CLASSES, 1, stride=(1, 1), pad=(0, 0), initialW=None, initial_bias=None), score4 = L.Deconvolution2D(CLASSES, CLASSES, (4,3), stride=(2, 2), pad=(1, 1), initialW=None, initial_bias=None), score_pool3 = L.Convolution2D(256, CLASSES, 1, stride=(1, 1), pad=(0, 0), initialW=None, initial_bias=None), upsample = L.Deconvolution2D(CLASSES, CLASSES, 8, stride=(8, 8), pad=(0, 0), initialW=None, initial_bias=None), ), self.name = name self.classes = CLASSES
def __init__(self): super(GEN, self).__init__( dc1=L.Convolution2D(None, 48, 5, 2, 2, wscale=0.02*math.sqrt(1*5*5)), fc2=L.Convolution2D(48, 128, 3, 1, 1, wscale=0.02*math.sqrt(48*3*3)), fc3=L.Convolution2D(128, 128, 3, 1, 1, wscale=0.02*math.sqrt(128*3*3)), dc4=L.Convolution2D(128, 256, 3, 2, 1, wscale=0.02*math.sqrt(128*3*3)), fc5=L.Convolution2D(256, 256, 3, 1, 1, wscale=0.02*math.sqrt(256*3*3)), fc6=L.Convolution2D(256, 256, 3, 1, 1, wscale=0.02*math.sqrt(256*3*3)), dc7=L.Convolution2D(256, 256, 3, 2, 1, wscale=0.02*math.sqrt(256*3*3)), fc8=L.Convolution2D(256, 512, 3, 1, 1, wscale=0.02*math.sqrt(256*3*3)), fc9=L.Convolution2D(512, 1024, 3, 1, 1, wscale=0.02*math.sqrt(512*3*3)), fc10=L.Convolution2D(1024, 1024, 3, 1, 1, wscale=0.02*math.sqrt(1024*3*3)), fc11=L.Convolution2D(1024, 1024, 3, 1, 1, wscale=0.02*math.sqrt(1024*3*3)), fc12=L.Convolution2D(1024, 1024, 3, 1, 1, wscale=0.02*math.sqrt(1024*3*3)), fc13=L.Convolution2D(1024, 512, 3, 1, 1, wscale=0.02*math.sqrt(1024*3*3)), fc14=L.Convolution2D(512, 256, 3, 1, 1, wscale=0.02*math.sqrt(512*3*3)), uc15=L.Deconvolution2D(256, 256, 4, 2, 1, wscale=0.02*math.sqrt(256*4*4)), fc16=L.Convolution2D(256, 256, 3, 1, 1, wscale=0.02*math.sqrt(256*3*3)), fc17=L.Convolution2D(256, 128, 3, 1, 1, wscale=0.02*math.sqrt(256*3*3)), uc18=L.Deconvolution2D(128, 128, 4, 2, 1, wscale=0.02*math.sqrt(128*4*4)), fc19=L.Convolution2D(128, 128, 3, 1, 1, wscale=0.02*math.sqrt(128*3*3)), fc20=L.Convolution2D(128, 48, 3, 1, 1, wscale=0.02*math.sqrt(128*3*3)), uc21=L.Deconvolution2D(48, 48, 4, 2, 1, wscale=0.02*math.sqrt(48*4*4)), fc22=L.Convolution2D(48, 24, 3, 1, 1, wscale=0.02*math.sqrt(48*3*3)), fc23=L.Convolution2D(24, 1, 3, 1, 1, wscale=0.02*math.sqrt(24*3*3)), bn1=L.BatchNormalization(48), bn2=L.BatchNormalization(128), bn3=L.BatchNormalization(128), bn4=L.BatchNormalization(256), bn5=L.BatchNormalization(256), bn6=L.BatchNormalization(256), bn7=L.BatchNormalization(256), bn8=L.BatchNormalization(512), bn9=L.BatchNormalization(1024), bn10=L.BatchNormalization(1024), bn11=L.BatchNormalization(1024), bn12=L.BatchNormalization(1024), bn13=L.BatchNormalization(512), bn14=L.BatchNormalization(256), bn15=L.BatchNormalization(256), bn16=L.BatchNormalization(256), bn17=L.BatchNormalization(128), bn18=L.BatchNormalization(128), bn19=L.BatchNormalization(128), bn20=L.BatchNormalization(48), bn21=L.BatchNormalization(48), bn22=L.BatchNormalization(24) )
def __init__(self): super(DilatedGEN, self).__init__( dc1=L.Convolution2D(None, 48, 5, 2, 2, wscale=0.02*math.sqrt(1*5*5)), fc2=L.Convolution2D(48, 128, 3, 1, 1, wscale=0.02*math.sqrt(48*3*3)), fc3=L.Convolution2D(128, 128, 3, 1, 1, wscale=0.02*math.sqrt(128*3*3)), dc4=L.Convolution2D(128, 256, 3, 2, 1, wscale=0.02*math.sqrt(128*3*3)), fc5=L.Convolution2D(256, 256, 3, 1, 1, wscale=0.02*math.sqrt(256*3*3)), fc6=L.Convolution2D(256, 256, 3, 1, 1, wscale=0.02*math.sqrt(256*3*3)), dc7=L.Convolution2D(256, 256, 3, 2, 1, wscale=0.02*math.sqrt(256*3*3)), fc8=L.Convolution2D(256, 512, 3, 1, 1, wscale=0.02*math.sqrt(256*3*3)), fc9=L.DilatedConvolution2D(512, 1024, 3, 1, 2, dilate=2, wscale=0.02*math.sqrt(512*3*3)), fc10=L.DilatedConvolution2D(1024, 1024, 3, 1, 4, dilate=4, wscale=0.02*math.sqrt(1024*3*3)), fc11=L.DilatedConvolution2D(1024, 1024, 3, 1, 8, dilate=8, wscale=0.02*math.sqrt(1024*3*3)), fc12=L.Convolution2D(1024, 1024, 3, 1, 1, wscale=0.02*math.sqrt(1024*3*3)), fc13=L.Convolution2D(1024, 512, 3, 1, 1, wscale=0.02*math.sqrt(1024*3*3)), fc14=L.Convolution2D(512, 256, 3, 1, 1, wscale=0.02*math.sqrt(512*3*3)), uc15=L.Deconvolution2D(256, 256, 4, 2, 1, wscale=0.02*math.sqrt(256*4*4)), fc16=L.Convolution2D(256, 256, 3, 1, 1, wscale=0.02*math.sqrt(256*3*3)), fc17=L.Convolution2D(256, 128, 3, 1, 1, wscale=0.02*math.sqrt(256*3*3)), uc18=L.Deconvolution2D(128, 128, 4, 2, 1, wscale=0.02*math.sqrt(128*4*4)), fc19=L.Convolution2D(128, 128, 3, 1, 1, wscale=0.02*math.sqrt(128*3*3)), fc20=L.Convolution2D(128, 48, 3, 1, 1, wscale=0.02*math.sqrt(128*3*3)), uc21=L.Deconvolution2D(48, 48, 4, 2, 1, wscale=0.02*math.sqrt(48*4*4)), fc22=L.Convolution2D(48, 24, 3, 1, 1, wscale=0.02*math.sqrt(48*3*3)), fc23=L.Convolution2D(24, 1, 3, 1, 1, wscale=0.02*math.sqrt(24*3*3)), bn1=L.BatchNormalization(48), bn2=L.BatchNormalization(128), bn3=L.BatchNormalization(128), bn4=L.BatchNormalization(256), bn5=L.BatchNormalization(256), bn6=L.BatchNormalization(256), bn7=L.BatchNormalization(256), bn8=L.BatchNormalization(512), bn9=L.BatchNormalization(1024), bn10=L.BatchNormalization(1024), bn11=L.BatchNormalization(1024), bn12=L.BatchNormalization(1024), bn13=L.BatchNormalization(512), bn14=L.BatchNormalization(256), bn15=L.BatchNormalization(256), bn16=L.BatchNormalization(256), bn17=L.BatchNormalization(128), bn18=L.BatchNormalization(128), bn19=L.BatchNormalization(128), bn20=L.BatchNormalization(48), bn21=L.BatchNormalization(48), bn22=L.BatchNormalization(24) )
def __init__(self): super(mGEN, self).__init__( dc1=L.Convolution2D(None, 48, 5, 2, 2, wscale=0.02 * math.sqrt(1 * 5 * 5)), fc2=L.Convolution2D(48, 128, 3, 1, 1, wscale=0.02 * math.sqrt(48 * 3 * 3)), fc3=L.Convolution2D(128, 128, 3, 1, 1, wscale=0.02 * math.sqrt(128 * 3 * 3)), dc4=L.Convolution2D(128, 256, 3, 2, 1, wscale=0.02 * math.sqrt(128 * 3 * 3)), fc5=L.Convolution2D(256, 256, 3, 1, 1, wscale=0.02 * math.sqrt(256 * 3 * 3)), fc6=L.Convolution2D(256, 256, 3, 1, 1, wscale=0.02 * math.sqrt(256 * 3 * 3)), dc7=L.Convolution2D(256, 256, 3, 2, 1, wscale=0.02 * math.sqrt(256 * 3 * 3)), fc8=L.Convolution2D(256, 512, 3, 1, 1, wscale=0.02 * math.sqrt(256 * 3 * 3)), fc9=L.DilatedConvolution2D(512, 1024, 3, 1, 2, dilate=2, wscale=0.02 * math.sqrt(512 * 3 * 3)), fc10=L.DilatedConvolution2D(1024, 1024, 3, 1, 4, dilate=4, wscale=0.02 * math.sqrt(1024 * 3 * 3)), fc11=L.DilatedConvolution2D(1024, 1024, 3, 1, 8, dilate=8, wscale=0.02 * math.sqrt(1024 * 3 * 3)), fc12=L.Convolution2D(1024, 1024, 3, 1, 1, wscale=0.02 * math.sqrt(1024 * 3 * 3)), fc13=L.Convolution2D(1024, 512, 3, 1, 1, wscale=0.02 * math.sqrt(1024 * 3 * 3)), fc14=L.Convolution2D(512, 256, 3, 1, 1, wscale=0.02 * math.sqrt(512 * 3 * 3)), uc15=L.Deconvolution2D(256, 256, 4, 2, 1, wscale=0.02 * math.sqrt(256 * 4 * 4)), fc16=L.Convolution2D(256, 256, 3, 1, 1, wscale=0.02 * math.sqrt(256 * 3 * 3)), fc17=L.Convolution2D(256, 128, 3, 1, 1, wscale=0.02 * math.sqrt(256 * 3 * 3)), uc18=L.Deconvolution2D(128, 128, 4, 2, 1, wscale=0.02 * math.sqrt(128 * 4 * 4)), fc19=L.Convolution2D(128, 128, 3, 1, 1, wscale=0.02 * math.sqrt(128 * 3 * 3)), fc20=L.Convolution2D(128, 48, 3, 1, 1, wscale=0.02 * math.sqrt(128 * 3 * 3)), uc21=L.Deconvolution2D(48, 48, 4, 2, 1, wscale=0.02 * math.sqrt(48 * 4 * 4)), fc22=L.Convolution2D(48, 24, 3, 1, 1, wscale=0.02 * math.sqrt(48 * 3 * 3)), fc23=L.Convolution2D(25, 1, 3, 1, 1, wscale=0.02 * math.sqrt(24 * 3 * 3)), bn1=L.BatchNormalization(48), bn2=L.BatchNormalization(128), bn3=L.BatchNormalization(128), bn4=L.BatchNormalization(256), bn5=L.BatchNormalization(256), bn6=L.BatchNormalization(256), bn7=L.BatchNormalization(256), bn8=L.BatchNormalization(512), bn9=L.BatchNormalization(1024), bn10=L.BatchNormalization(1024), bn11=L.BatchNormalization(1024), bn12=L.BatchNormalization(1024), bn13=L.BatchNormalization(512), bn14=L.BatchNormalization(256), bn15=L.BatchNormalization(256), bn16=L.BatchNormalization(256), bn17=L.BatchNormalization(128), bn18=L.BatchNormalization(128), bn19=L.BatchNormalization(128), bn20=L.BatchNormalization(48), bn21=L.BatchNormalization(48), bn22=L.BatchNormalization(24) )
def __init__(self, VGGModel=None, n_class=15): if VGGModel is None: self.wb = load_VGGmodel() else: self.wb = VGGModel self.n_class = n_class # layers which is trained super(HumanPartsNet, self).__init__( conv1_1=L.Convolution2D( 3, 64, 3, stride=1, pad=100, initialW=self.wb["conv1_1_W"], initial_bias=self.wb["conv1_1_b"]), conv1_2=L.Convolution2D( 64, 64, 3, stride=1, pad=1, initialW=self.wb["conv1_2_W"], initial_bias=self.wb["conv1_2_b"]), conv2_1=L.Convolution2D( 64, 128, 3, stride=1, pad=1, initialW=self.wb["conv2_1_W"], initial_bias=self.wb["conv2_1_b"]), conv2_2=L.Convolution2D(128, 128, 3, stride=1, pad=1, initialW=self.wb["conv2_2_W"], initial_bias=self.wb["conv2_2_b"]), conv3_1=L.Convolution2D(128, 256, 3, stride=1, pad=1, initialW=self.wb["conv3_1_W"], initial_bias=self.wb["conv3_1_b"]), conv3_2=L.Convolution2D(256, 256, 3, stride=1, pad=1, initialW=self.wb["conv3_2_W"], initial_bias=self.wb["conv3_2_b"]), conv3_3=L.Convolution2D(256, 256, 3, stride=1, pad=1, initialW=self.wb["conv3_3_W"], initial_bias=self.wb["conv3_3_b"]), conv4_1=L.Convolution2D(256, 512, 3, stride=1, pad=1, initialW=self.wb["conv4_1_W"], initial_bias=self.wb["conv4_1_b"]), conv4_2=L.Convolution2D(512, 512, 3, stride=1, pad=1, initialW=self.wb["conv4_2_W"], initial_bias=self.wb["conv4_2_b"]), conv4_3=L.Convolution2D(512, 512, 3, stride=1, pad=1, initialW=self.wb["conv4_3_W"], initial_bias=self.wb["conv4_3_b"]), conv5_1=L.Convolution2D(512, 512, 3, stride=1, pad=1, initialW=self.wb["conv5_1_W"], initial_bias=self.wb["conv5_1_b"]), conv5_2=L.Convolution2D(512, 512, 3, stride=1, pad=1, initialW=self.wb["conv5_2_W"], initial_bias=self.wb["conv5_2_b"]), conv5_3=L.Convolution2D(512, 512, 3, stride=1, pad=1, initialW=self.wb["conv5_3_W"], initial_bias=self.wb["conv5_3_b"]), upsample_pool1=L.Convolution2D(64, self.n_class, ksize=1, stride=1, pad=0, wscale=0.01), upsample_pool2=L.Convolution2D(128, self.n_class, ksize=1, stride=1, pad=0, wscale=0.01), upsample_pool3=L.Convolution2D(256, self.n_class, ksize=1, stride=1, pad=0, wscale=0.01), upsample_pool4=L.Convolution2D(512, self.n_class, ksize=1, stride=1, pad=0, wscale=0.01), fc6_conv=L.Convolution2D(512, 4096, 7, stride=1, pad=0, initialW=self.wb["fc6_W"], initial_bias=self.wb["fc6_b"]), fc7_conv=L.Convolution2D(4096, 4096, 1, stride=1, pad=0, initialW=self.wb["fc7_W"], initial_bias=self.wb["fc7_b"]), upconv1=L.Deconvolution2D(4096, self.n_class, ksize= 4, stride=2, pad=0, nobias=True, initialW=self.get_deconv_filter([4, 4, self.n_class, 4096])), upconv2=L.Deconvolution2D(self.n_class, self.n_class, ksize= 4, stride=2, pad=0, nobias=True, initialW=self.get_deconv_filter([4, 4, self.n_class, self.n_class])), upconv3=L.Deconvolution2D(self.n_class, self.n_class, ksize= 4, stride=2, pad=0, nobias=True, initialW=self.get_deconv_filter([4, 4, self.n_class, self.n_class])), upconv4=L.Deconvolution2D(self.n_class, self.n_class, ksize= 4, stride=2, pad=0, nobias=True, initialW=self.get_deconv_filter([4, 4, self.n_class, self.n_class])), upconv5=L.Deconvolution2D(self.n_class, self.n_class, ksize= 4, stride=2, pad=0, nobias=True, initialW=self.get_deconv_filter([4, 4, self.n_class, self.n_class])), ) self.train = True del self.wb
