pytorch入门之变量

Tensor

Tenosr是一种和numpy的ndarrays是相同的概念，不同的时tensor可以用GPU来加速

#import sys

#sys.executable

​

#print(sys.path)

​

from __future__ import print_function

import torch

x = torch.Tensor(5, 3)

print(x)


1.00000e-31 *
 -5.0975  0.0000 -5.0975
  0.0000  0.0000  0.0000
  0.0000  0.0000  0.0000
  0.0000  0.0000  0.0000
  0.0000  0.0000  0.0000
[torch.FloatTensor of size 5x3]

x = torch.rand(5, 3)

print(x)

print(x.size())


 0.3834  0.8875  0.3252
 0.9993  0.6884  0.9710
 0.3140  0.4587  0.9075
 0.0496  0.9154  0.4637
 0.6238  0.2553  0.4406
[torch.FloatTensor of size 5x3]

torch.Size([5, 3])

y = torch.rand(5, 3)

print(x + y)

​

print(torch.add(x, y))


 0.4426  1.2303  0.8045
 1.1960  1.1696  1.3620
 0.4249  0.5298  1.0216
 0.0576  1.3974  0.7120
 0.7984  0.5635  0.7325
[torch.FloatTensor of size 5x3]


 0.4426  1.2303  0.8045
 1.1960  1.1696  1.3620
 0.4249  0.5298  1.0216
 0.0576  1.3974  0.7120
 0.7984  0.5635  0.7325
[torch.FloatTensor of size 5x3]

result = torch.Tensor(5, 3)

torch.add(x, y, out = result)

print(result)


 0.4426  1.2303  0.8045
 1.1960  1.1696  1.3620
 0.4249  0.5298  1.0216
 0.0576  1.3974  0.7120
 0.7984  0.5635  0.7325
[torch.FloatTensor of size 5x3]

如果想通过一个操作改变tensor的内容可以用带下滑线的操作，如x.copy(y), x.t()，将会改变x的操作

y.add_(x)

print(y)


 0.4426  1.2303  0.8045
 1.1960  1.1696  1.3620
 0.4249  0.5298  1.0216
 0.0576  1.3974  0.7120
 0.7984  0.5635  0.7325
[torch.FloatTensor of size 5x3]

torch变量与numpy可以方便的链接起来

a = torch.ones(5)

print(a)


 1
 1
 1
 1
 1
[torch.FloatTensor of size 5]

b = a.numpy()

print(b)

[ 1.  1.  1.  1.  1.]

将numpy变量转为tensor变量

import numpy as np

a = np.ones(5)

b = torch.from_numpy(a)

np.add(a, 1, out = a)

print(a)

print(b)

[ 2.  2.  2.  2.  2.]

 2
 2
 2
 2
 2
[torch.DoubleTensor of size 5]