(一) easy pytorch

from __future__ import print_function
import torch

x = torch.empty(5, 3)
print(x)

tensor([[-3.9455e+14,  4.5659e-41, -3.9455e+14],
        [ 4.5659e-41,         nan,  0.0000e+00],
        [ 7.6194e+31,  1.5564e+28,  1.8484e+31],
        [ 1.8370e+25,  1.4603e-19,  2.7517e+12],
        [ 7.5338e+28,  3.0313e+32,  6.3828e+28]])

x = torch.rand(5, 3)
print(x)

tensor([[0.6871, 0.4370, 0.3990],
        [0.0113, 0.2071, 0.4084],
        [0.4247, 0.1985, 0.3557],
        [0.9084, 0.2724, 0.9430],
        [0.9945, 0.9366, 0.2340]])

x = torch.zeros(5, 3, dtype = torch.long)
print(x)

tensor([[0, 0, 0],
        [0, 0, 0],
        [0, 0, 0],
        [0, 0, 0],
        [0, 0, 0]])

x = torch.tensor([5.5, 3])
print(x)

tensor([5.5000, 3.0000])

x = x.new_ones(5, 3, dtype = torch.double)
print(x)

x = torch.randn_like(x, dtype = torch.float)
print(x)

tensor([[1., 1., 1.],
        [1., 1., 1.],
        [1., 1., 1.],
        [1., 1., 1.],
        [1., 1., 1.]], dtype=torch.float64)
tensor([[ 0.4788, -0.3258,  0.8718],
        [-0.1653,  0.6451, -0.0676],
        [-0.4569,  0.0050, -0.2013],
        [-0.2161, -1.4332,  0.4315],
        [ 1.2185,  1.3106,  1.2528]])

print(x.size())

torch.Size([5, 3])

x.size()[0]

5

y = torch.rand(5, 3)
print(x + y)

tensor([[ 0.6953,  0.4946,  1.3985],
        [ 0.0877,  0.6795,  0.4029],
        [ 0.1927,  0.3577,  0.7364],
        [ 0.4793, -0.4866,  1.0796],
        [ 1.8104,  1.4822,  1.7686]])

print(torch.add(x, y))

tensor([[ 0.6953,  0.4946,  1.3985],
        [ 0.0877,  0.6795,  0.4029],
        [ 0.1927,  0.3577,  0.7364],
        [ 0.4793, -0.4866,  1.0796],
        [ 1.8104,  1.4822,  1.7686]])

result = torch.empty(5, 3)
torch.add(x, y, out = result)
print(result)

tensor([[ 0.6953,  0.4946,  1.3985],
        [ 0.0877,  0.6795,  0.4029],
        [ 0.1927,  0.3577,  0.7364],
        [ 0.4793, -0.4866,  1.0796],
        [ 1.8104,  1.4822,  1.7686]])

y.add_(x)
print(y)

tensor([[ 0.6953,  0.4946,  1.3985],
        [ 0.0877,  0.6795,  0.4029],
        [ 0.1927,  0.3577,  0.7364],
        [ 0.4793, -0.4866,  1.0796],
        [ 1.8104,  1.4822,  1.7686]])

print(x[:, 1])

tensor([-0.3258,  0.6451,  0.0050, -1.4332,  1.3106])

x = torch.randn(4, 4)
y = x.view(16)
z = x.view(-1, 8)
print(x.size(), y.size(), z.size())
print(x)
print(y)
print(z)

torch.Size([4, 4]) torch.Size([16]) torch.Size([2, 8])
tensor([[ 0.5526, -2.0670, -1.2156, -0.3779],
        [-1.8972,  0.6599, -0.8264,  1.0419],
        [-0.1237,  0.5389, -0.0888,  0.9985],
        [-0.0256,  0.4312, -1.0118, -0.2873]])
tensor([ 0.5526, -2.0670, -1.2156, -0.3779, -1.8972,  0.6599, -0.8264,  1.0419,
        -0.1237,  0.5389, -0.0888,  0.9985, -0.0256,  0.4312, -1.0118, -0.2873])
tensor([[ 0.5526, -2.0670, -1.2156, -0.3779, -1.8972,  0.6599, -0.8264,  1.0419],
        [-0.1237,  0.5389, -0.0888,  0.9985, -0.0256,  0.4312, -1.0118, -0.2873]])

x = torch.randn(1)
print(x)
print(x.item())

tensor([1.5204])
1.5204463005065918

a = torch.ones(5)
print(a)

tensor([1., 1., 1., 1., 1.])

b = a.numpy()
print(b)

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

a.add_(1)
print(a)
print(b)

tensor([2., 2., 2., 2., 2.])
[2. 2. 2. 2. 2.]

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.]
tensor([2., 2., 2., 2., 2.], dtype=torch.float64)

if torch.cuda.is_available():
    device = torch.device('cuda')
    y = torch.ones_like(x, device=device)
    x = x.to(device)
    z = x+y
    print(z.to('cpu',dtype=torch.double))

tensor([2.5204], dtype=torch.float64)

该内容模仿自pytorch官网 ：original url