Traceback (most recent call last): File "E:/pycharm/AHEcode/train.py", line 229, in <module> outputs = model(images) File "E:\conda\CONDA\envs\hu-torch\lib\site-packages\torch\nn\modules\module.py", line 1130, in _call_impl return forward_call(*input, **kwargs) File "E:/pycharm/AHEcode/train.py", line 63, in forward x_final = torch.cat([x3_flat, lbp_output], dim=1) # 将 x3_flat 和 lbp_output 拼接 RuntimeError: Sizes of tensors must match except in dimension 1. Expected size 6272 but got size 8 for tensor number 1 in the list.完整的代码如下： def forward(self, x): x1 = F.relu(self.bn1(torch.cat([self.conv1_3x3(x), self.conv1_5x5(x), self.conv1_7x7(x)], dim=1))) x1 = F.max_pool2d(x1, 2) x2 = F.relu(self.bn2(torch.cat([self.conv2_3x3(x1), self.conv2_5x5(x1), self.conv2_7x7(x1)], dim=1))) x2 = F.max_pool2d(x2, 2) x3 = F.relu(self.bn3(torch.cat([self.conv3_3x3(x2), self.conv3_5x5(x2), self.conv3_7x7(x2)], dim=1))) x3 = F.max_pool2d(x3, 2) x3_flat = x3.view(-1, 768) print(f'x3_flat size: {x3_flat.size()}') clahe_output = self.clahe_module(x) print(clahe_output.shape) lbp_output = self.lbp_layer(clahe_output) print(f'lbp_output size: {lbp_output.size()}') lbp_output = lbp_output.to(x3_flat.device) # print(f'lbp_output expanded size: {lbp_output.size()}') x_final = torch.cat([x3_flat, lbp_output], dim=1) # 将 x3_flat 和 lbp_output 拼接 output = self.fc(x_final) # 全连接层得到最终的输出 return output

这个错误是因为在 torch.cat 操作中，除了第 1 维度以外，其他维度的大小应该是相同的，但是在你的代码中，x3_flat 的大小是 [batch_size, 768]，而 lbp_output 的大小是 [batch_size, 1, height, width]，没有经过展平操作，因此维度不匹配。你可以将 lbp_output 展平成 [batch_size, height*width]，然后再进行拼接操作。修改后的代码如下：

def forward(self, x):
    x1 = F.relu(self.bn1(torch.cat([self.conv1_3x3(x), self.conv1_5x5(x), self.conv1_7x7(x)], dim=1)))
    x1 = F.max_pool2d(x1, 2)
    x2 = F.relu(self.bn2(torch.cat([self.conv2_3x3(x1), self.conv2_5x5(x1), self.conv2_7x7(x1)], dim=1)))
    x2 = F.max_pool2d(x2, 2)
    x3 = F.relu(self.bn3(torch.cat([self.conv3_3x3(x2), self.conv3_5x5(x2), self.conv3_7x7(x2)], dim=1)))
    x3 = F.max_pool2d(x3, 2)
    
    x3_flat = x3.view(-1, 768)
    print(f'x3_flat size: {x3_flat.size()}')
    
    clahe_output = self.clahe_module(x)
    print(clahe_output.shape)

    lbp_output = self.lbp_layer(clahe_output)
    lbp_output = lbp_output.view(lbp_output.size(0), -1)  # 将 lbp_output 展平
    print(f'lbp_output size: {lbp_output.size()}')
    
    lbp_output = lbp_output.to(x3_flat.device)
    x_final = torch.cat([x3_flat, lbp_output], dim=1)  # 将 x3_flat 和 lbp_output 拼接
    output = self.fc(x_final)  # 全连接层得到最终的输出
    return output

这样修改后，应该就可以正常运行了。