我正在开发一个全卷积自编码器，它接受3个通道作为输入，并输出2个通道（输入：LAB，输出：AB）。因为输出应该与输入大小相同，所以我使用了全卷积。
代码如下：
import torch.nn as nnclass AE(nn.Module): def __init__(self): super(AE, self).__init__() self.encoder = nn.Sequential( # conv 1 nn.Conv2d(in_channels=3, out_channels=64, kernel_size=5, stride=1, padding=1), nn.BatchNorm2d(64), nn.ReLU(), nn.MaxPool2d(kernel_size=2, stride=2), # conv 2 nn.Conv2d(in_channels=64, out_channels=128, kernel_size=5, stride=1, padding=1), nn.BatchNorm2d(128), nn.ReLU(), nn.MaxPool2d(kernel_size=2, stride=2), # conv 3 nn.Conv2d(in_channels=128, out_channels=256, kernel_size=5, stride=1, padding=1), nn.BatchNorm2d(256), nn.ReLU(), nn.MaxPool2d(kernel_size=2, stride=2), # conv 4 nn.Conv2d(in_channels=256, out_channels=512, kernel_size=5, stride=1, padding=1), nn.BatchNorm2d(512), nn.ReLU(), nn.MaxPool2d(kernel_size=2, stride=2), # conv 5 nn.Conv2d(in_channels=512, out_channels=1024, kernel_size=5, stride=1, padding=1), nn.BatchNorm2d(1024), nn.ReLU() ) self.decoder = nn.Sequential( # conv 6 nn.ConvTranspose2d(in_channels=1024, out_channels=512, kernel_size=5, stride=1, padding=1), nn.BatchNorm2d(512), nn.ReLU(), # conv 7 nn.Upsample(scale_factor=2, mode='bilinear'), nn.ConvTranspose2d(in_channels=512, out_channels=256, kernel_size=5, stride=1, padding=1), nn.BatchNorm2d(256), nn.ReLU(), # conv 8 nn.Upsample(scale_factor=2, mode='bilinear'), nn.ConvTranspose2d(in_channels=256, out_channels=128, kernel_size=5, stride=1, padding=1), nn.BatchNorm2d(128), nn.ReLU(), # conv 9 nn.Upsample(scale_factor=2, mode='bilinear'), nn.ConvTranspose2d(in_channels=128, out_channels=64, kernel_size=5, stride=1, padding=1), nn.BatchNorm2d(64), nn.ReLU(), # conv 10 out nn.Upsample(scale_factor=2, mode='bilinear'), nn.ConvTranspose2d(in_channels=64, out_channels=2, kernel_size=5, stride=1, padding=1), nn.Softmax() # multi-class classification # TODO softmax deprecated ) def forward(self, x): x = self.encoder(x) x = self.decoder(x) return x输出张量应该的大小是：torch.Size([1, 2, 199, 253])
输出张量实际的大小是：torch.Size([1, 2, 190, 238])
我的主要问题是如何结合Conv2d和MaxPool2d，以及如何在ConvTranspose2d中设置正确的参数值。因此，我分别处理它们，使用Upsample函数处理MaxPool2d，而仅对Conv2d使用ConvTranspose2d。但我仍然存在一些不对称性，我实在不知道原因。
感谢您的帮助！
回答：
存在两个问题。
首先是填充不足：当kernel_size=5时，每次应用卷积都会使图像缩小4个像素（每边2个像素），所以在所有地方都需要padding=2，而不仅仅是1。
其次是输入大小“不均匀”。我的意思是，一旦你的卷积被正确填充，你就剩下降采样操作，这些操作在每个点上尝试将图像分辨率减半。当它们失败时，它们只返回一个较小的结果（整数除法会丢弃余数）。由于你的网络有4个连续的2倍降采样操作，你需要输入的H, W维度是2^4=16的倍数。这样你实际上会得到形状相同的输出。下面是一个示例：
import torchimport torch.nn as nnclass AE(nn.Module): def __init__(self): super(AE, self).__init__() self.encoder = nn.Sequential( # conv 1 nn.Conv2d(in_channels=3, out_channels=64, kernel_size=5, stride=1, padding=2), nn.BatchNorm2d(64), nn.ReLU(), nn.MaxPool2d(kernel_size=2, stride=2), # conv 2 nn.Conv2d(in_channels=64, out_channels=128, kernel_size=5, stride=1, padding=2), nn.BatchNorm2d(128), nn.ReLU(), nn.MaxPool2d(kernel_size=2, stride=2), # conv 3 nn.Conv2d(in_channels=128, out_channels=256, kernel_size=5, stride=1, padding=2), nn.BatchNorm2d(256), nn.ReLU(), nn.MaxPool2d(kernel_size=2, stride=2), # conv 4 nn.Conv2d(in_channels=256, out_channels=512, kernel_size=5, stride=1, padding=2), nn.BatchNorm2d(512), nn.ReLU(), nn.MaxPool2d(kernel_size=2, stride=2), # conv 5 nn.Conv2d(in_channels=512, out_channels=1024, kernel_size=5, stride=1, padding=2), nn.BatchNorm2d(1024), nn.ReLU() ) self.decoder = nn.Sequential( # conv 6 nn.ConvTranspose2d(in_channels=1024, out_channels=512, kernel_size=5, stride=1, padding=2), nn.BatchNorm2d(512), nn.ReLU(), # conv 7 nn.Upsample(scale_factor=2, mode='bilinear'), nn.ConvTranspose2d(in_channels=512, out_channels=256, kernel_size=5, stride=1, padding=2), nn.BatchNorm2d(256), nn.ReLU(), # conv 8 nn.Upsample(scale_factor=2, mode='bilinear'), nn.ConvTranspose2d(in_channels=256, out_channels=128, kernel_size=5, stride=1, padding=2), nn.BatchNorm2d(128), nn.ReLU(), # conv 9 nn.Upsample(scale_factor=2, mode='bilinear'), nn.ConvTranspose2d(in_channels=128, out_channels=64, kernel_size=5, stride=1, padding=2), nn.BatchNorm2d(64), nn.ReLU(), # conv 10 out nn.Upsample(scale_factor=2, mode='bilinear'), nn.ConvTranspose2d(in_channels=64, out_channels=2, kernel_size=5, stride=1, padding=2), nn.Softmax() # multi-class classification ) def forward(self, x): x = self.encoder(x) x = self.decoder(x) return xinput = torch.randn(1, 3, 6*16, 7*16)output = AE()(input)print(input.shape)print(output.shape)