使用 pytorch 卷积 model 时出现运行时错误

Question

I'm trying to develop a covid-19 classification model. The images dataset I used is of shape torch.Size([100, 3, 224, 224]). When trying to run my model I'm getting this runtime error message(as shown in the image). Any help to understand and fix the issue, please. this is the code

class CovidCnnModel(ImageClassificationBase):
def __init__(self):
    super().__init__()
    self.network = nn.Sequential(
      # nn.Conv2d(in_channels, out_channels, kernel_size =(3,3), padding=1),
        nn.Conv2d(3, out_channels = 32, kernel_size=3, padding=1),
        nn.ReLU(),
        nn.Conv2d(32, 64, kernel_size=3, stride=1, padding=1),
        nn.ReLU(),
        nn.MaxPool2d(2, 2), # output: 64 x 16 x 16

        nn.Conv2d(64, 128, kernel_size=3, stride=1, padding=1),
        nn.ReLU(),
        nn.Conv2d(128, 128, kernel_size=3, stride=1, padding=1),
        nn.ReLU(),
        nn.MaxPool2d(2, 2), # output: 128 x 8 x 8

        nn.Conv2d(128, 256, kernel_size=3, stride=1, padding=1),
        nn.ReLU(),
        nn.Conv2d(256, 256, kernel_size=3, stride=1, padding=1),
        nn.ReLU(),
        nn.MaxPool2d(2, 2), # output: 256 x 4 x 4

        nn.Flatten(), 
        nn.Linear(256*4*4, 1024),
        nn.ReLU(),
        nn.Linear(1024, 512),
        nn.ReLU(),
        nn.Linear(512, 2))
    
def forward(self, xb):
    return self.network(xb)

Answer 1

Your input is of size 224x224 while your network is designed for ``128x128` (judging by the comments in the code).