RuntimeError: Expected 4-dimensional input for 4-dimensional weight [1024, 64, 3, 3], but got input of size [32, 10] instead

Question

This line works fine

self.conv = nn.Conv2d(3, 64, kernel_size=3, stride=2, padding=1, bias=False)

I introduced ResNet18

self.conv          


        

Answer 1

The problem is that resnet18 (and most other classification netwroks) are not fully convolutional networks. The last layer of the net is actually a nn.Linear layer and therefore you cannot simply replace a convolutional block/layer with a resnet.