Python torch.nn 模块，ConvTranspose2d() 实例源码
我们从Python开源项目中，提取了以下50个代码示例，用于说明如何使用torch.nn.ConvTranspose2d()。
def __init__(self):
super(ImageTransformNet, self).__init__()
self.conv1 = nn.Conv2d(3, 32, kernel_size=9, stride=1, padding=4)
self.bn1 = nn.Batchnorm2d(32)
self.conv2 = nn.Conv2d(32, 64, kernel_size=4, stride=2, padding=1)
self.bn2 = nn.Batchnorm2d(64)
self.conv3 = nn.Conv2d(64, 128, padding=1)
self.bn3 = nn.Batchnorm2d(128)
self.res1 = ResidualBlock(128, 128)
self.res2 = ResidualBlock(128, 128)
self.res3 = ResidualBlock(128, 128)
self.res4 = ResidualBlock(128, 128)
self.res5 = ResidualBlock(128, 128)
self.conv4 = nn.ConvTranspose2d(128, padding=1)
self.bn4 = nn.Batchnorm2d(64)
self.conv5 = nn.ConvTranspose2d(64, padding=1)
self.bn5 = nn.Batchnorm2d(32)
self.conv6 = nn.ConvTranspose2d(32, 3, padding=4)
def __init__(self, prior_size):
super(DCGenerator, self).__init__()
self.prior_size = prior_size
self.linear1 = nn.Linear(prior_size, 4*4*512)
# 4x4 --> 8x8
self.deconv1 = nn.ConvTranspose2d(512, 256, (5,5))
# Batch normalization
self.bn1 = nn.Batchnorm2d(256)
# 8x8 --> 16x16,stride 2
self.deconv2 = nn.ConvTranspose2d(256,5), stride = (2,2), padding = (2, output_padding = (1,1))
# Batch normalization
self.bn2 = nn.Batchnorm2d(128)
# 16x16 --> 32x32,stride
self.deconv3 = nn.ConvTranspose2d(128,1))
def __init__(self):
super(StylePart, padding=4)
self.bn1 = nn.Batchnorm2d(32)
self.conv2 = nn.Conv2d(32, padding=1)
self.bn2 = nn.Batchnorm2d(64)
self.conv3 = nn.Conv2d(64, padding=1)
self.bn3 = nn.Batchnorm2d(128)
self.res1 = ResBlock(128)
self.res2 = ResBlock(128)
self.res3 = ResBlock(128)
self.res4 = ResBlock(128)
self.res5 = ResBlock(128)
self.deconv1 = nn.ConvTranspose2d(128, padding=1)
self.bn4 = nn.Batchnorm2d(64)
self.deconv2 = nn.ConvTranspose2d(64, padding=1)
self.bn5 = nn.Batchnorm2d(32)
self.deconv3 = nn.Conv2d(32, padding=4)
def buildNetGbg(self, nsize): # take vector as input,and outout bgimg
net = nn.Sequential()
size_map = 1
name = str(size_map)
net.add_module('convt' + name, nn.ConvTranspose2d(nz, ngf * 4, 4, 0, bias=True))
net.add_module('bn' + name, nn.Batchnorm2d(ngf * 4))
net.add_module('relu' + name, nn.ReLU(True))
size_map = 4
depth_in = 4 * ngf
depth_out = 2 * ngf
while size_map < nsize / 2:
name = str(size_map)
net.add_module('convt' + name, nn.ConvTranspose2d(depth_in, depth_out, 2, 1, bias=True))
net.add_module('bn' + name, nn.Batchnorm2d(depth_out))
net.add_module('relu' + name, nn.ReLU(True))
depth_in = depth_out
depth_out = max(depth_in / 2, 64)
size_map = size_map * 2
return net, depth_in
def buildNetGfg(self,and output fgimg and fgmask
net = nn.Sequential()
size_map = 1
name = str(size_map)
net.add_module('convt' + name, ngf * 8, bias=False))
net.add_module('bn' + name, nn.Batchnorm2d(ngf * 8))
net.add_module('relu' + name, nn.ReLU(True))
size_map = 4
depth_in = 8 * ngf
depth_out = 4 * ngf
while size_map < nsize / 2:
name = str(size_map)
net.add_module('convt' + name, bias=False))
net.add_module('bn' + name, depth_in
def __init__(self, num_classes, pretrained=True):
super(FCN32VGG, self).__init__()
vgg = models.vgg16()
if pretrained:
vgg.load_state_dict(torch.load(vgg16_caffe_path))
features, classifier = list(vgg.features.children()), list(vgg.classifier.children())
features[0].padding = (100, 100)
for f in features:
if 'MaxPool' in f.__class__.__name__:
f.ceil_mode = True
elif 'ReLU' in f.__class__.__name__:
f.inplace = True
self.features5 = nn.Sequential(*features)
fc6 = nn.Conv2d(512, 4096, kernel_size=7)
fc6.weight.data.copy_(classifier[0].weight.data.view(4096, 512, 7, 7))
fc6.bias.data.copy_(classifier[0].bias.data)
fc7 = nn.Conv2d(4096, kernel_size=1)
fc7.weight.data.copy_(classifier[3].weight.data.view(4096, 1))
fc7.bias.data.copy_(classifier[3].bias.data)
score_fr = nn.Conv2d(4096, kernel_size=1)
score_fr.weight.data.zero_()
score_fr.bias.data.zero_()
self.score_fr = nn.Sequential(
fc6, nn.ReLU(inplace=True), nn.Dropout(), fc7, score_fr
)
self.upscore = nn.ConvTranspose2d(num_classes, kernel_size=64, stride=32, bias=False)
self.upscore.weight.data.copy_(get_upsampling_weight(num_classes, 64))
def __init__(self, in_channels, out_channels, num_conv_layers):
super(_DecoderBlock, self).__init__()
middle_channels = in_channels / 2
layers = [
nn.ConvTranspose2d(in_channels, kernel_size=2, stride=2),
nn.Conv2d(in_channels, middle_channels, kernel_size=3, padding=1),
nn.Batchnorm2d(middle_channels),
nn.ReLU(inplace=True)
]
layers += [
nn.Conv2d(middle_channels,
nn.Batchnorm2d(middle_channels),
nn.ReLU(inplace=True),
] * (num_conv_layers - 2)
layers += [
nn.Conv2d(middle_channels,
nn.Batchnorm2d(out_channels),
nn.ReLU(inplace=True),
]
self.decode = nn.Sequential(*layers)
def __init__(self, num_points = 2048):
super(PointGenPSG, self).__init__()
self.num_points = num_points
self.fc1 = nn.Linear(100, 256)
self.fc2 = nn.Linear(256, 512)
self.fc3 = nn.Linear(512, 1024)
self.fc4 = nn.Linear(1024, self.num_points / 4 * 3 * 1)
self.th = nn.Tanh()
self.conv1 = nn.ConvTranspose2d(100,1024,(2,3))
self.conv2 = nn.ConvTranspose2d(1024, 1)
self.conv3 = nn.ConvTranspose2d(512, 1)
self.conv4= nn.ConvTranspose2d(256, 1)
self.conv5= nn.ConvTranspose2d(128, 1)
self.bn1 = torch.nn.Batchnorm2d(1024)
self.bn2 = torch.nn.Batchnorm2d(512)
self.bn3 = torch.nn.Batchnorm2d(256)
self.bn4 = torch.nn.Batchnorm2d(128)
self.bn5 = torch.nn.Batchnorm2d(3)
def make_conv_layer(layer_list, in_dim, out_dim, back_conv, batch_norm=True, activation='ReLU', k_s_p=[4,2,1]):
k, s, p = k_s_p[0], k_s_p[1], k_s_p[2]
if back_conv == False:
layer_list.append(nn.Conv2d(in_dim, kernel_size=k, stride=s, padding=p, bias=False))
elif back_conv == True:
layer_list.append(nn.ConvTranspose2d(in_dim, bias=False))
if batch_norm == True:
layer_list.append(nn.Batchnorm2d(out_dim))
if activation == 'ReLU':
layer_list.append(nn.ReLU(True))
elif activation == 'Sigmoid':
layer_list.append(nn.Sigmoid())
elif activation == 'Tanh':
layer_list.append(nn.Tanh())
elif activation == 'LeakyReLU':
layer_list.append(nn.LeakyReLU(0.2, inplace=True))
return layer_list
def __init__(self, params, nclasses, encoder):
super().__init__()
self.encoder = encoder
self.pooling_modules = []
for mod in self.encoder.modules():
try:
if mod.other.downsample:
self.pooling_modules.append(mod.other)
except AttributeError:
pass
self.layers = []
for i, params in enumerate(params):
if params['upsample']:
params['pooling_module'] = self.pooling_modules.pop(-1)
layer = DecoderModule(**params)
self.layers.append(layer)
layer_name = 'decoder{:02d}'.format(i)
super().__setattr__(layer_name, layer)
self.output_conv = nn.ConvTranspose2d(16, padding=0, output_padding=0, bias=True)
def __init__(self, numClasses, prelus=False):
super().__init__()
self.upsampler7 = upsamplerA(128, 128)
self.conv7 = nonBt1d(128, 0.1, prelus, 1)
self.upsampler6 = upsamplerA(128, 128)
self.conv6 = nonBt1d(128, 1)
self.upsampler5 = upsamplerA(128, 128)
self.conv5 = nonBt1d(128, 1)
self.upsampler4 = upsamplerA(128, 128)
self.conv4 = nonBt1d(128, 1)
self.upsampler3 = upsamplerA(128, 128)
self.conv3 = nonBt1d(128, 1)
self.upsampler2 = upsamplerA(128, 64)
self.conv2a = nonBt1d(64, 2)
self.conv2b = nonBt1d(64, 4)
self.upsampler1 = upsamplerB(64, numClasses)
self.conv1a = nonBt1d(numClasses, 2)
self.conv1b = nonBt1d(numClasses, 4)
self.conv1c = nonBt1d(numClasses, 8)
self.convFinal = nn.ConvTranspose2d(numClasses, stride=2)
def __init__(self, ngpu):
super(_netG, self).__init__()
self.ngpu = ngpu
self.main = nn.Sequential(
# input is Z,going into a convolution
nn.ConvTranspose2d( nz, bias=False),
nn.Batchnorm2d(ngf * 8),
nn.ReLU(True),
# state size. (ngf*8) x 4 x 4
nn.ConvTranspose2d(ngf * 8,
nn.Batchnorm2d(ngf * 4),
# state size. (ngf*4) x 8 x 8
nn.ConvTranspose2d(ngf * 4, ngf * 2,
nn.Batchnorm2d(ngf * 2),
# state size. (ngf*2) x 16 x 16
nn.ConvTranspose2d(ngf * 2, ngf,
nn.Batchnorm2d(ngf),
# state size. (ngf) x 32 x 32
nn.ConvTranspose2d( ngf, nc,
nn.Tanh()
# state size. (nc) x 64 x 64
)
def get_parameters(model, bias=False):
import torch.nn as nn
modules_skipped = (
nn.ReLU,
nn.MaxPool2d,
nn.Dropout2d,
nn.Sequential,
torchfcn.models.FCN32s,
torchfcn.models.FCN16s,
torchfcn.models.FCN8s,
)
for m in model.modules():
if isinstance(m, nn.Conv2d):
if bias:
yield m.bias
else:
yield m.weight
elif isinstance(m, nn.ConvTranspose2d):
# weight is frozen because it is just a bilinear upsampling
if bias:
assert m.bias is None
elif isinstance(m, modules_skipped):
continue
else:
raise ValueError('Unexpected module: %s' % str(m))
def __init__(self):
super(Generator, self).__init__()
self.main = nn.Sequential(
nn.ConvTranspose2d(nz,
nn.ConvTranspose2d(ngf * 8,
nn.ConvTranspose2d(ngf * 4,
nn.ConvTranspose2d(ngf * 2, ngf * 1,
nn.Batchnorm2d(ngf * 1),
nn.ConvTranspose2d(ngf * 1, nc,
nn.Tanh()
)
self.apply(weights_init)
self.optimizer = optim.Adam(self.parameters(), lr=learning_rate, betas=(beta_1, beta_2))
#self.optimizer = optim.RMSprop(self.parameters(),lr=learning_rate,alpha=beta_2)
def __init__(self, ngf, hidden_size, condition=False, condition_size=0):
super(Decoder, self).__init__()
self.condition = condition
self.decode_cond = nn.ConvTranspose2d(condition_size, kernel_size=8,stride=1,padding=0)
# 1
self.decode = nn.ConvTranspose2d(hidden_size,padding=0)
# 8
self.dconv6 = deconv_block(ngf*2, ngf)
# 16
self.dconv5 = deconv_block(ngf, ngf)
# 32
self.dconv4 = deconv_block(ngf, ngf)
# 64
self.dconv3 = deconv_block(ngf, ngf)
# 128
#self.dconv2 = deconv_block(ngf,ngf)
# 256
self.dconv1 = nn.Sequential(nn.Conv2d(ngf,ngf,kernel_size=3,padding=1),
nn.ELU(True),
nn.Conv2d(ngf,
nn.Tanh())
def __init__(self, self).__init__()
self.ngpu = ngpu
self.main = nn.Sequential(
# b,nz,1,1
nn.ConvTranspose2d(nz, 28 * 28,
# b,28*28,1
nn.Batchnorm2d(28 * 28),
nn.ConvTranspose2d(28 * 28, 14 * 14,14*14,2,2
nn.Batchnorm2d(14 * 14),
nn.ConvTranspose2d(14 * 14, 7 * 7,7*7,4,4
nn.Batchnorm2d(7 * 7),
nn.ConvTranspose2d(7 * 7, stride=7,
# b. 1,28,28
nn.Sigmoid()
)
def __init__(self):
super(Generator, self).__init__()
self.model = nn.Sequential(
nn.Linear(z_dim+10, 4*4*256),
nn.LeakyReLU()
)
self.cnn = nn.Sequential(
nn.ConvTranspose2d(256, output_padding=0),
nn.LeakyReLU(),
nn.ConvTranspose2d(128, padding=1,
nn.ConvTranspose2d(64, padding=2, output_padding=1),
nn.Conv2d(64,
nn.Tanh()
)
def __init__(self):
super(Generator, self).__init__()
self.layer1 = nn.Sequential(
nn.Conv2d(1, 16, # 28*28 -> 14*14
nn.Batchnorm2d(16),
nn.LeakyReLU()
)
self.layer2 = nn.Sequential(
nn.Conv2d(16, # 14*14 -> 14*14
nn.Batchnorm2d(16),
nn.LeakyReLU()
)
self.layer3 = nn.Sequential(
nn.ConvTranspose2d(16, # 14*14 -> 28*28
nn.Tanh()
)
def __init__(self, ngpu):
super(NetG,
nn.Tanh()
# state size. (nc) x 64 x 64
)
def __init__(self, stride, bias=True):
super(deconv2DBatchnormRelu, self).__init__()
self.dcbr_unit = nn.Sequential(nn.ConvTranspose2d(int(in_channels),
padding=padding,
nn.ReLU(inplace=True), in_size, out_size, is_deconv):
super(unetUp, self).__init__()
self.conv = unetConv2(in_size, False)
if is_deconv:
self.up = nn.ConvTranspose2d(in_size, stride=2)
else:
self.up = nn.UpsamplingBilinear2d(scale_factor=2)
def _initialize_weights(self):
vgg16 = torchvision.models.vgg16(pretrained=True)
for m in self.modules():
if isinstance(m, nn.ConvTranspose2d):
assert m.kernel_size[0] == m.kernel_size[1]
m.weight.data = weight_init.kaiming_normal(m.weight.data)
for a, b in zip(vgg16.features, self.features):
if (isinstance(a, nn.Conv2d) and isinstance(b, nn.Conv2d)):
b.weight.data = a.weight.data
b.bias.data = a.bias.data
for i in [0, 3]:
a, b = vgg16.classifier[i], self.classifier[i]
b.weight.data = a.weight.data.view(b.weight.size())
b.bias.data = a.bias.data.view(b.bias.size())
def U_weight_init(ms):
for m in ms.modules():
classname = m.__class__.__name__
if classname.find('Conv2d') != -1:
m.weight.data = init.kaiming_normal(m.weight.data, a=0.2)
elif classname.find('ConvTranspose2d') != -1:
m.weight.data = init.kaiming_normal(m.weight.data)
print ('worked!') # Todo: kill this
elif classname.find('Batchnorm') != -1:
m.weight.data.normal_(1.0, 0.02)
m.bias.data.fill_(0)
elif classname.find('Linear') != -1:
m.weight.data = init.kaiming_normal(m.weight.data)
def deconv(c_in, c_out, pad=1, bn=True):
"""Custom deconvolutional layer for simplicity."""
layers = []
layers.append(nn.ConvTranspose2d(c_in, pad, bias=False))
if bn:
layers.append(nn.Batchnorm2d(c_out))
return nn.Sequential(*layers)
def __init__(self, input_nc, output_nc, ngf=64, norm_layer=nn.Batchnorm2d, use_dropout=False, n_blocks=6, gpu_ids=[]):
assert(n_blocks >= 0)
super(resnetGenerator, self).__init__()
self.input_nc = input_nc
self.output_nc = output_nc
self.ngf = ngf
self.gpu_ids = gpu_ids
model = [nn.Conv2d(input_nc, kernel_size=7, padding=3),
norm_layer(ngf, affine=True),
nn.ReLU(True)]
n_downsampling = 2
for i in range(n_downsampling):
mult = 2**i
model += [nn.Conv2d(ngf * mult, ngf * mult * 2,
stride=2,
norm_layer(ngf * mult * 2,
nn.ReLU(True)]
mult = 2**n_downsampling
for i in range(n_blocks):
model += [resnetBlock(ngf * mult, 'zero', norm_layer=norm_layer, use_dropout=use_dropout)]
for i in range(n_downsampling):
mult = 2**(n_downsampling - i)
model += [nn.ConvTranspose2d(ngf * mult, int(ngf * mult / 2),
kernel_size=3,
padding=1,
norm_layer(int(ngf * mult / 2),
nn.ReLU(True)]
model += [nn.Conv2d(ngf, padding=3)]
model += [nn.Tanh()]
self.model = nn.Sequential(*model)
def __init__(self, outer_nc, inner_nc,
submodule=None, outermost=False, innermost=False, use_dropout=False):
super(UnetSkipConnectionBlock, self).__init__()
self.outermost = outermost
downconv = nn.Conv2d(outer_nc,
stride=2, padding=1)
downrelu = nn.LeakyReLU(0.2, True)
downnorm = norm_layer(inner_nc, affine=True)
uprelu = nn.ReLU(True)
upnorm = norm_layer(outer_nc, affine=True)
if outermost:
upconv = nn.ConvTranspose2d(inner_nc * 2,
kernel_size=4,
padding=1)
down = [downconv]
up = [uprelu, upconv, nn.Tanh()]
model = down + [submodule] + up
elif innermost:
upconv = nn.ConvTranspose2d(inner_nc,
padding=1)
down = [downrelu, downconv]
up = [uprelu, upnorm]
model = down + up
else:
upconv = nn.ConvTranspose2d(inner_nc * 2, downconv, downnorm]
up = [uprelu, upnorm]
if use_dropout:
model = down + [submodule] + up + [nn.Dropout(0.5)]
else:
model = down + [submodule] + up
self.model = nn.Sequential(*model)
def test_ConvTranspose2d_output_size(self):
m = nn.ConvTranspose2d(3, 2)
i = Variable(torch.randn(2, 6, 6))
for h in range(15, 22):
for w in range(15, 22):
if 18 <= h <= 20 and 18 <= w <= 20:
size = (h, w)
if h == 19:
size = torch.LongStorage(size)
elif h == 2:
size = torch.LongStorage((2, 4) + size)
m(i, output_size=(h, w))
else:
self.assertRaises(ValueError, lambda: m(i, (h, w)))
def __init__(self, n_channel_input, n_channel_output, n_filters):
super(G, self).__init__()
self.conv1 = nn.Conv2d(n_channel_input, 1)
self.conv2 = nn.Conv2d(n_filters, n_filters * 2, 1)
self.conv3 = nn.Conv2d(n_filters * 2, n_filters * 4, 1)
self.conv4 = nn.Conv2d(n_filters * 4, n_filters * 8, 1)
self.conv5 = nn.Conv2d(n_filters * 8, 1)
self.conv6 = nn.Conv2d(n_filters * 8, 1)
self.conv7 = nn.Conv2d(n_filters * 8, 1)
self.conv8 = nn.Conv2d(n_filters * 8, 1)
self.deconv1 = nn.ConvTranspose2d(n_filters * 8, 1)
self.deconv2 = nn.ConvTranspose2d(n_filters * 8 * 2, 1)
self.deconv3 = nn.ConvTranspose2d(n_filters * 8 * 2, 1)
self.deconv4 = nn.ConvTranspose2d(n_filters * 8 * 2, 1)
self.deconv5 = nn.ConvTranspose2d(n_filters * 8 * 2, 1)
self.deconv6 = nn.ConvTranspose2d(n_filters * 4 * 2, 1)
self.deconv7 = nn.ConvTranspose2d(n_filters * 2 * 2, 1)
self.deconv8 = nn.ConvTranspose2d(n_filters * 2, 1)
self.batch_norm = nn.Batchnorm2d(n_filters)
self.batch_norm2 = nn.Batchnorm2d(n_filters * 2)
self.batch_norm4 = nn.Batchnorm2d(n_filters * 4)
self.batch_norm8 = nn.Batchnorm2d(n_filters * 8)
self.leaky_relu = nn.LeakyReLU(0.2, True)
self.relu = nn.ReLU(True)
self.dropout = nn.Dropout(0.5)
self.tanh = nn.Tanh()
def __init__(self, out_h, out_w, channel_dims, z_dim=100):
super().__init__()
assert len(channel_dims) == 4, "length of channel dims should be 4"
conv1_dim, conv2_dim, conv3_dim, conv4_dim = channel_dims
conv1_h, conv2_h, conv3_h, conv4_h = map(conv_size, [(out_h, step) for step in [4 ,3 ,2 ,1]])
conv1_w, conv2_w, conv3_w, conv4_w = map(conv_size, [(out_w,1]])
self.fc = nn.Linear(z_dim, conv1_dim*conv1_h*conv1_w)
self.deconvs = nn.Sequential(
nn.Batchnorm2d(conv1_dim),
nn.ReLU(),
nn.ConvTranspose2d(conv1_dim,
nn.Batchnorm2d(conv2_dim),
nn.ConvTranspose2d(conv2_dim,
nn.Batchnorm2d(conv3_dim),
nn.ConvTranspose2d(conv3_dim, conv4_dim,
nn.Batchnorm2d(conv4_dim),
nn.ConvTranspose2d(conv4_dim,
nn.Tanh(),
)
self.conv1_size = (conv1_dim, conv1_h, conv1_w)
self._init_weight()
def _init_weight(self):
self.fc.weight.data.normal_(.0, 0.02)
for layer in self.deconvs:
if isinstance(layer, nn.ConvTranspose2d):
layer.weight.data.normal_(.0, 0.02)
if isinstance(layer, nn.Batchnorm2d):
layer.weight.data.normal_(1., 0.02)
layer.bias.data.fill_(0)
def deconv(c_in, bias=False))
if bn:
layers.append(nn.Batchnorm2d(c_out))
return nn.Sequential(*layers)
def __init__(self, out_channels):
super(Generator, self).__init__()
self.c0 = nn.Conv2d(in_channels, padding=1)
self.c1 = nn.Conv2d(64, padding=1)
self.c2 = nn.Conv2d(128, padding=1)
self.c3 = nn.Conv2d(256, padding=1)
self.c4 = nn.Conv2d(512, padding=1)
self.c5 = nn.Conv2d(512, padding=1)
self.c6 = nn.Conv2d(512, padding=1)
self.c7 = nn.Conv2d(512, padding=1)
self.d7 = nn.ConvTranspose2d(512, padding=1)
self.d6 = nn.ConvTranspose2d(1024, padding=1)
self.d5 = nn.ConvTranspose2d(1024, padding=1)
self.d4 = nn.ConvTranspose2d(1024, padding=1)
self.d3 = nn.ConvTranspose2d(1024, padding=1)
self.d2 = nn.ConvTranspose2d(512, padding=1)
self.d1 = nn.ConvTranspose2d(256, padding=1)
self.d0 = nn.ConvTranspose2d(128, padding=1)
self.bnc1 = nn.Batchnorm2d(128)
self.bnc2 = nn.Batchnorm2d(256)
self.bnc3 = nn.Batchnorm2d(512)
self.bnc4 = nn.Batchnorm2d(512)
self.bnc5 = nn.Batchnorm2d(512)
self.bnc6 = nn.Batchnorm2d(512)
self.bnd7 = nn.Batchnorm2d(512)
self.bnd6 = nn.Batchnorm2d(512)
self.bnd5 = nn.Batchnorm2d(512)
self.bnd4 = nn.Batchnorm2d(512)
self.bnd3 = nn.Batchnorm2d(256)
self.bnd2 = nn.Batchnorm2d(128)
self.bnd1 = nn.Batchnorm2d(64)
def __init__(self, isize, k=100, ngf=64):
super(Decoder, self).__init__()
assert isize % 16 == 0, "isize has to be a multiple of 16"
cngf, tisize = ngf // 2, 4
while tisize != isize:
cngf = cngf * 2
tisize = tisize * 2
main = nn.Sequential()
main.add_module('initial.{0}-{1}.convt'.format(k, cngf), nn.ConvTranspose2d(k, cngf, bias=False))
main.add_module('initial.{0}.batchnorm'.format(cngf), nn.Batchnorm2d(cngf))
main.add_module('initial.{0}.relu'.format(cngf), nn.ReLU(True))
csize = 4
while csize < isize // 2:
main.add_module('pyramid.{0}-{1}.convt'.format(cngf, cngf // 2),
nn.ConvTranspose2d(cngf, cngf // 2, bias=False))
main.add_module('pyramid.{0}.batchnorm'.format(cngf // 2),
nn.Batchnorm2d(cngf // 2))
main.add_module('pyramid.{0}.relu'.format(cngf // 2),
nn.ReLU(True))
cngf = cngf // 2
csize = csize * 2
main.add_module('final.{0}-{1}.convt'.format(cngf, nc), nn.ConvTranspose2d(cngf, bias=False))
main.add_module('final.{0}.tanh'.format(nc),
nn.Tanh())
self.main = main
def deconv(c_in, pad))
if bn:
layers.append(nn.Batchnorm2d(c_out))
return nn.Sequential(*layers)
def __init__(self,batchnorm=True):
super(FlowNetS,self).__init__()
self.batchnorm = batchnorm
self.conv1 = conv(self.batchnorm, 6, 64, stride=2)
self.conv2 = conv(self.batchnorm, 64, 128, kernel_size=5, stride=2)
self.conv3 = conv(self.batchnorm, 256, stride=2)
self.conv3_1 = conv(self.batchnorm, 256)
self.conv4 = conv(self.batchnorm, 512, stride=2)
self.conv4_1 = conv(self.batchnorm, 512)
self.conv5 = conv(self.batchnorm, stride=2)
self.conv5_1 = conv(self.batchnorm, 512)
self.conv6 = conv(self.batchnorm, stride=2)
self.conv6_1 = conv(self.batchnorm, 1024)
self.deconv5 = deconv(1024,512)
self.deconv4 = deconv(1026,256)
self.deconv3 = deconv(770,128)
self.deconv2 = deconv(386,64)
self.predict_flow6 = predict_flow(1024)
self.predict_flow5 = predict_flow(1026)
self.predict_flow4 = predict_flow(770)
self.predict_flow3 = predict_flow(386)
self.predict_flow2 = predict_flow(194)
self.upsampled_flow6_to_5 = nn.ConvTranspose2d(2, bias=False)
self.upsampled_flow5_to_4 = nn.ConvTranspose2d(2, bias=False)
self.upsampled_flow4_to_3 = nn.ConvTranspose2d(2, bias=False)
self.upsampled_flow3_to_2 = nn.ConvTranspose2d(2, bias=False)
for m in self.modules():
if isinstance(m, nn.Conv2d) or isinstance(m, nn.ConvTranspose2d):
kaiming_normal(m.weight.data)
if m.bias is not None:
m.bias.data.zero_()
elif isinstance(m, nn.Batchnorm2d):
m.weight.data.fill_(1)
m.bias.data.zero_()
def upconv2x2(in_channels, mode='transpose'):
if mode == 'transpose':
return nn.ConvTranspose2d(
in_channels,
out_channels,
kernel_size=2,
stride=2)
else:
# out_channels is always going to be the same
# as in_channels
return nn.Sequential(
nn.Upsample(mode='bilinear', scale_factor=2),
conv1x1(in_channels, out_channels))
def __init__(self, bn=False, num_classes=10):
super(CMTL, self).__init__()
self.num_classes = num_classes
self.base_layer = nn.Sequential(Conv2d( 1, 9, same_padding=True, NL='prelu', bn=bn),
Conv2d(16, bn=bn))
self.hl_prior_1 = nn.Sequential(Conv2d( 32,
nn.MaxPool2d(2),
Conv2d(16,
Conv2d(32, 8, 7, bn=bn))
self.hl_prior_2 = nn.Sequential(nn.AdaptiveMaxPool2d((32,32)),
Conv2d( 8, bn=bn))
self.hl_prior_fc1 = FC(4*1024,512, NL='prelu')
self.hl_prior_fc2 = FC(512,256, NL='prelu')
self.hl_prior_fc3 = FC(256, self.num_classes, NL='prelu')
self.de_stage_1 = nn.Sequential(Conv2d( 32, 20,
Conv2d(20, 40, 5,
Conv2d(40, 10, bn=bn))
self.de_stage_2 = nn.Sequential(Conv2d( 18, 24,
Conv2d( 24,
nn.ConvTranspose2d(32,16,4,stride=2,padding=1,output_padding=0,bias=True),
nn.PReLU(),
nn.ConvTranspose2d(16,8,
Conv2d(8, NL='relu', bn=bn))
def __init__(self, in_: int, out: int, *, bn=True, activation='relu', up='upconv'):
super().__init__()
self.l1 = Conv3BN(in_, out, bn, activation)
self.l2 = Conv3BN(out, activation)
if up == 'upconv':
self.up = nn.ConvTranspose2d(in_, stride=2)
elif up == 'upsample':
self.up = nn.Upsample(scale_factor=2)
版权声明：本文内容由互联网用户自发贡献，该文观点与技术仅代表作者本人。本站仅提供信息存储空间服务，不拥有所有权，不承担相关法律责任。如发现本站有涉嫌侵权/违法违规的内容， 请发送邮件至 dio@foxmail.com 举报，一经查实，本站将立刻删除。
