# Codeblock 3 Output
x & residual    : torch.Size([1, 96, 56, 56])
after conv0     : torch.Size([1, 96, 56, 56])  
after permute   : torch.Size([1, 56, 56, 96])    #(1)
after norm      : torch.Size([1, 56, 56, 96])
after permute   : torch.Size([1, 96, 56, 56])    #(2)
after conv1     : torch.Size([1, 384, 56, 56])   #(3)
after gelu      : torch.Size([1, 384, 56, 56])
after conv2     : torch.Size([1, 96, 56, 56])    #(4)
after summation : torch.Size([1, 96, 56, 56])