我正在使用 GAN，我得到了伪像，删除它们的最佳方法是将生成器块 conv2dtranspose 更改为上采样和卷积，正如许多论文所建议的那样。我正在尝试通过我的个人数据集生成 ASL 手形符号
这是上面屏幕截图中提到的暗示 conv2dtranspose 的块代码
def _block(self, in_channels, out_channels, kernel_size, stride, padding):
return nn.Sequential(
nn.ConvTranspose2d(
in_channels, out_channels, kernel_size, stride, padding, bias=False,
),
nn.BatchNorm2d(out_channels),
nn.LeakyReLU(0.2),
我想要实现的是更改块，以便它对图像进行采样并对其应用卷积，从而产生与 conv2dTranspose 相同的输出图像大小
这是我试过的
nn.Upsample(scale_factor = 2, mode='bilinear'),
nn.ReflectionPad2d(1),
nn.Conv2d(out_channels, int(out_channels / 2),kernel_size=3, stride=1, padding=0),
nn.BatchNorm2d(out_channels),
nn.LeakyReLU(0.2),
但是我收到以下错误 [![enter image description here][3]][3]
---------------------------------------------------------------------------
RuntimeError Traceback (most recent call last)
<ipython-input-12-4fa61054bc2c> in <module>
81 for _ in range(CRITIC_ITERATIONS):
82 noise = torch.randn(cur_batch_size, Z_DIM, 1, 1).to(device)
---> 83 fake = gen(noise,labels)
84 critic_real = critic(real,labels).reshape(-1)
85 critic_fake = critic(fake,labels).reshape(-1)
~\Anaconda3\lib\site-packages\torch\nn\modules\module.py in _call_impl(self, *input, **kwargs)
725 result = self._slow_forward(*input, **kwargs)
726 else:
--> 727 result = self.forward(*input, **kwargs)
728 for hook in itertools.chain(
729 _global_forward_hooks.values(),
<ipython-input-10-6af8005acf1f> in forward(self, x, labels)
77 embedding=self.embed(labels).unsqueeze(2).unsqueeze(3)
78 x=torch.cat([x,embedding],dim=1)
---> 79 return self.net(x)
80
81
~\Anaconda3\lib\site-packages\torch\nn\modules\module.py in _call_impl(self, *input, **kwargs)
725 result = self._slow_forward(*input, **kwargs)
726 else:
--> 727 result = self.forward(*input, **kwargs)
728 for hook in itertools.chain(
729 _global_forward_hooks.values(),
~\Anaconda3\lib\site-packages\torch\nn\modules\container.py in forward(self, input)
115 def forward(self, input):
116 for module in self:
--> 117 input = module(input)
118 return input
119
~\Anaconda3\lib\site-packages\torch\nn\modules\module.py in _call_impl(self, *input, **kwargs)
725 result = self._slow_forward(*input, **kwargs)
726 else:
--> 727 result = self.forward(*input, **kwargs)
728 for hook in itertools.chain(
729 _global_forward_hooks.values(),
~\Anaconda3\lib\site-packages\torch\nn\modules\container.py in forward(self, input)
115 def forward(self, input):
116 for module in self:
--> 117 input = module(input)
118 return input
119
~\Anaconda3\lib\site-packages\torch\nn\modules\module.py in _call_impl(self, *input, **kwargs)
725 result = self._slow_forward(*input, **kwargs)
726 else:
--> 727 result = self.forward(*input, **kwargs)
728 for hook in itertools.chain(
729 _global_forward_hooks.values(),
~\Anaconda3\lib\site-packages\torch\nn\modules\conv.py in forward(self, input)
421
422 def forward(self, input: Tensor) -> Tensor:
--> 423 return self._conv_forward(input, self.weight)
424
425 class Conv3d(_ConvNd):
~\Anaconda3\lib\site-packages\torch\nn\modules\conv.py in _conv_forward(self, input, weight)
418 _pair(0), self.dilation, self.groups)
419 return F.conv2d(input, weight, self.bias, self.stride,
--> 420 self.padding, self.dilation, self.groups)
421
422 def forward(self, input: Tensor) -> Tensor:
RuntimeError: Given groups=1, weight of size [1024, 2048, 1, 1], expected input[64, 200, 2, 2] to have 2048 channels, but got 200 channels instead
此外，如果我将步幅更改为 1，它会给我嵌入错误
=================================================================
Layer (type:depth-idx) Param #
=================================================================
├─Sequential: 1-1 --
| └─Sequential: 2-1 --
| | └─Upsample: 3-1 --
| | └─Conv2d: 3-2 411,648
| | └─BatchNorm2d: 3-3 4,096
| | └─LeakyReLU: 3-4 --
| └─Sequential: 2-2 --
| | └─Upsample: 3-5 --
| | └─Conv2d: 3-6 2,098,176
| | └─BatchNorm2d: 3-7 2,048
| | └─LeakyReLU: 3-8 --
| └─Sequential: 2-3 --
| | └─Upsample: 3-9 --
| | └─Conv2d: 3-10 524,800
| | └─BatchNorm2d: 3-11 1,024
| | └─LeakyReLU: 3-12 --
| └─Sequential: 2-4 --
| | └─Upsample: 3-13 --
| | └─Conv2d: 3-14 131,328
| | └─BatchNorm2d: 3-15 512
| | └─LeakyReLU: 3-16 --
| └─Sequential: 2-5 --
| | └─Upsample: 3-17 --
| | └─Conv2d: 3-18 32,896
| | └─BatchNorm2d: 3-19 256
| | └─LeakyReLU: 3-20 --
| └─ConvTranspose2d: 2-6 6,147
| └─Tanh: 2-7 --
├─Embedding: 1-2 2,700
=================================================================
Total params: 3,215,631
Trainable params: 3,215,631
Non-trainable params: 0
=================================================================
=================================================================
Layer (type:depth-idx) Param #
=================================================================
├─Sequential: 1-1 --
| └─Conv2d: 2-1 2,080
| └─LeakyReLU: 2-2 --
| └─Sequential: 2-3 --
| | └─Conv2d: 3-1 32,768
| | └─InstanceNorm2d: 3-2 128
| | └─LeakyReLU: 3-3 --
| └─Sequential: 2-4 --
| | └─Conv2d: 3-4 131,072
| | └─InstanceNorm2d: 3-5 256
| | └─LeakyReLU: 3-6 --
| └─Sequential: 2-5 --
| | └─Conv2d: 3-7 524,288
| | └─InstanceNorm2d: 3-8 512
| | └─LeakyReLU: 3-9 --
| └─Sequential: 2-6 --
| | └─Conv2d: 3-10 2,097,152
| | └─InstanceNorm2d: 3-11 1,024
| | └─LeakyReLU: 3-12 --
| └─Conv2d: 2-7 8,193
├─Embedding: 1-2 442,368
=================================================================
Total params: 3,239,841
Trainable params: 3,239,841
Non-trainable params: 0
=================================================================
---------------------------------------------------------------------------
RuntimeError Traceback (most recent call last)
<ipython-input-3-4fa61054bc2c> in <module>
83 fake = gen(noise,labels)
84 critic_real = critic(real,labels).reshape(-1)
---> 85 critic_fake = critic(fake,labels).reshape(-1)
86 gp = gradient_penalty(critic,labels, real, fake, device=device)
87 loss_critic = (
~\Anaconda3\lib\site-packages\torch\nn\modules\module.py in _call_impl(self, *input, **kwargs)
725 result = self._slow_forward(*input, **kwargs)
726 else:
--> 727 result = self.forward(*input, **kwargs)
728 for hook in itertools.chain(
729 _global_forward_hooks.values(),
<ipython-input-1-4154f5f318f2> in forward(self, x, labels)
38 def forward(self, x,labels):
39 embedding=self.embed(labels).view(labels.shape[0],1,self.img_size,self.img_size)
---> 40 x=torch.cat([x,embedding],dim=1)
41 return self.disc(x)
42
RuntimeError: Sizes of tensors must match except in dimension 2. Got 128 and 64 (The offending index is 0)
有人可以解释我将如何为我的架构实现这一目标。