PyTorch中的view函數(shù)可以改變tensor的形狀

eg1

import torch
test = torch.zeros(2,3)
print(test)
print(test.view(3,-1)) #-1表示程序會(huì)根據(jù)上一個(gè)維度自動(dòng)計(jì)算-1所在位置的維度

#tensor([[0., 0., 0.],
#        [0., 0., 0.]])

#tensor([[0., 0.],
#        [0., 0.],
#        [0., 0.]])

eg2

test = torch.Tensor([1,2,3,4,5,6,7,8])
print(test)
print(test.view(4,2))

# tensor([1., 2., 3., 4., 5., 6., 7., 8.])

#tensor([[1., 2.],
#        [3., 4.],
#        [5., 6.],
#        [7., 8.]])