Python- pytorch基本操作tensor应用

1. 查看tensor版本

import torch
torch.__version__

‘1.6.0’

2. 创建全0小数

x = torch.empty(5, 3)
x
tensor([[8.9082e-39, 9.9184e-39, 8.4490e-39],
        [9.6429e-39, 1.0653e-38, 1.0469e-38],
        [4.2246e-39, 1.0378e-38, 9.6429e-39],
        [9.2755e-39, 9.7346e-39, 1.0745e-38],
        [1.0102e-38, 9.9184e-39, 2.3111e-33]])

3. 创建随即数据

x = torch.rand(5, 3)
x
tensor([[0.6977, 0.4890, 0.9416],
        [0.1685, 0.4124, 0.8846],
        [0.8664, 0.9411, 0.5017],
        [0.6676, 0.9020, 0.4379],
        [0.8681, 0.1378, 0.6282]])

4. 创建0矩阵

x = torch.zeros(5, 3, dtype=torch.long)
x
tensor([[0, 0, 0],
        [0, 0, 0],
        [0, 0, 0],
        [0, 0, 0],
        [0, 0, 0]])