Pytorch 学习 - 1.pytorch 张量基本操作

1.张量基本操作简介与创建

1.1 torch.zeros

import torch
out_t =torch.tensor([1])
t = torch.zeros((4,4),out=out_t)

print('t :', t, '\n','out_t :', out_t)
print(id(t),id(out_t))

output

t : tensor([[0, 0, 0, 0],
        [0, 0, 0, 0],
        [0, 0, 0, 0],
        [0, 0, 0, 0]]) 
 out_t : tensor([[0, 0, 0, 0],
        [0, 0, 0, 0],
        [0, 0, 0, 0],
        [0, 0, 0, 0]])
2777186850912 2777186850912

out_t 与t 共用内存

1.2 torch.ones

import torch
out_t =torch.tensor([1])
t = torch.ones((3,3),out=out_t)
print('t :', t, '\n', out_t)
print(id(t),id(out_t))

output
t : tensor([[1, 1, 1],
        [1, 1, 1],
        [1, 1, 1]]) 
 tensor([[1, 1, 1],
        [1, 1, 1],
        [1, 1, 1]])
2777187916752 2777187916752

1.3 torch.full

import torch
out_t =torch.tensor([1])
t = torch.full((3,3),4,out=out_t)
print('t :', t, '\n', out_t)
print(id(t),id(out_t))

output

t : tensor([[4, 4, 4],
        [4, 4, 4],
        [4, 4, 4]]) 
 tensor([[4, 4, 4],
        [4, 4, 4],
        [4, 4, 4]])
2776837717504 2776837717504

1.4 torch.full_like