import torch
parser = argparse.ArgumentParser(description='PyTorch')
parser.add_argument('--img_w', default=144, type=int, metavar='imgw', help='img width')
parser.add_argument('--img_h', default=288, type=int, metavar='imgh', help='img height')
parser.add_argument('--batch-size', default=32, type=int,metavar='B', help='training batch size')
parser.add_argument('--test-batch', default=64, type=int, metavar='tb', help='testing batch size')
 
class net(nn.Module):
 def __init__(self, arch='resnet18'):
 super(net, self).__init__()
 model_ft = models.resnet50(pretrained=True)
 self.visible = model_ft
 
 def forward(self, x):
 print(x.shape)
 print(x.size())
 print(x.ndim)
 
 input = self.visible.conv1(x)
 
 print(input.shape)
 print(input.size())
 print(input.ndim)

>import torch
>a = torch.Tensor([[[1, 2, 3], [4, 5, 6]]])
>a.size()
torch.Size([1, 2, 3])

> b=a.view(-1, 3, 2)
> b
tensor([[[1., 2.],
  [3., 4.],
  [5., 6.]]])
> b.size()
torch.Size([1, 3, 2])

> b.squeeze(2).size()
torch.Size([1, 3, 2])
> b.squeeze(0).size()
torch.Size([3, 2])

> b.unsqueeze(2).size()
torch.Size([1, 3, 1, 2])
> b.unsqueeze(2)
tensor([[[[1., 2.]],

  [[3., 4.]],

  [[5., 6.]]]])

> b.permute(2, 0, 1).size()
torch.Size([2, 1, 3])
> b.permute(2, 0, 1)
tensor([[[1., 3., 5.]],

 [[2., 4., 6.]]])