np.newaxis,tensor.squeeze(),np.hstack,torch.hstack,torch.cat,tensor.reshape的使用

np.newaxis,tensor.squeeze()的作用比较相似，增加维度。

np.hstack,torch.hstack,torch.cat([tensor,tensor],dim=1) 比较相似，连接tensor。

import torch
import numpy as np

if __name__ == '__main__':
    print(torch.__version__)
    # labels = torch.tensor([0, 1, 2, 0, 1, 2, 0, 1, 2])
    a = np.array([1,2,3,4])
    a_new = np.array([5,6,7,8])[:,np.newaxis]
    b = a[:,np.newaxis]
    print(b)
    b_new = np.hstack([b,a_new])
    print(b_new)
    c = torch.tensor([1,2,3,4])
    c_new = torch.tensor([5,6,7,8]).unsqueeze(1)
    d = c.unsqueeze(1)
    print(d)
    d_new = torch.hstack([d,c_new])
    print(d_new)
    e = torch.cat([d, c_new],dim=1)
    print(e)
    f = e.reshape([2,4])
    print(e,f)

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