Pytorch 基础

Pytorch 1.0.0 学习笔记：

Pytorch 的学习可以参考：Welcome to PyTorch Tutorials

Pytorch 是什么？

快速上手 Pytorch!

Tensors(张量)

from __future__ import print_function
import torch

创建一个没有初始化的 \(5\times 3\) 矩阵：

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

tensor([[0.0000e+00, 0.0000e+00, 0.0000e+00],
        [0.0000e+00, 0.0000e+00, 0.0000e+00],
        [0.0000e+00, 0.0000e+00, 0.0000e+00],
        [0.0000e+00, 1.9730e-42, 0.0000e+00],
        [0.0000e+00, 7.3909e+22, 0.0000e+00]])

创建一个已经初始化的 \(5\times 3\) 的随机矩阵：

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

tensor([[0.2496, 0.8405, 0.7555],
        [0.9820, 0.9988, 0.5419],
        [0.6570, 0.4990, 0.4165],
        [0.6985, 0.9972, 0.4234],
        [0.0096, 0.6374, 0.8520]])

给定数据类型为 long 的 \(5\times 3\) 的全零矩阵：

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]])

直接从 list 中创建张量：

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

tensor([5.5000, 3.0000])

直接从 Numpy 中创建张量：

import numpy as np
a = np.array([2, 3, 5], dtype='B')
x = torch.tensor(a)  # numpy
print(x)
x.numel()  # Tensor 中元素的个数

tensor([2, 3, 5], dtype=torch.uint8)
3

x = torch.rand(5, 3)
size = x.size()
print(size)
h, w = size
h, w

torch.Size([5, 3])
(5, 3)

Operations(运算)

Tensor 的运算大都与 Numpy 相同，下面仅仅介绍一些特殊的运算方式：

x = x.new_ones(5, 3, dtype=torch.double)      # new_* methods take in sizes
print(x)
x = torch.randn_like(x, dtype=torch.float)    # override dtype!
print(x)

tensor([[1., 1., 1.],
        [1., 1., 1.],
        [1., 1., 1.],
        [1., 1., 1.],
        [1., 1., 1.]], dtype=torch.float64)
tensor([[-0.9367, -0.1121,  1.9103],
        [ 0.2284,  0.3823,  1.0877],
        [-0.2797,  0.7217, -0.7032],
        [ 0.9047,  1.7789,  0.4215],
        [-1.0368, -0.2644, -0.7948]])

result = torch.empty(5, 3)  # 创建一个为初始化的矩阵
y = torch.rand(5, 3)
torch.add(x, y, out=result) # 计算 x + y 并将结果赋值给 result
print(result)

tensor([[-0.0202,  0.6110,  2.8150],
        [ 1.0288,  1.2454,  1.7464],
        [-0.1786,  0.8212, -0.2493],
        [ 1.5294,  2.2713,  0.8383],
        [-0.9292,  0.5749, -0.1146]])

任何一个 可变的 tensor 所对应的运算在其适当的位置后加上 _， 便会修改原 tensor 的值：

x = torch.tensor([7])
y = torch.tensor([2])
print(y, y.add(x))
print(y, y.add_(x))
y

tensor([2]) tensor([9])
tensor([9]) tensor([9])
tensor([9])

x = torch.tensor(7)
x.item()  # 转换为 python 的 number

7

reshape tensor：veiw()

x = torch.randn(4, 4)
y = x.view(16)
z = x.view(-1, 8)  # the size -1 is inferred from other dimensions
print(x.size(), y.size(), z.size())

torch.Size([4, 4]) torch.Size([16]) torch.Size([2, 8])

NumPy Bridge(与 Numpy 交互)

Tensor 转换为 Numpy

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

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

Tensor 转换为 Numpy

b = a.numpy()
print(b)

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

_ 的作用依然存在：

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

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

Numpy 转换为 Tensor

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)

CUDA

使用 .to 方法，Tensors 可被移动到任何 device：

# let us run this cell only if CUDA is available
# We will use ``torch.device`` objects to move tensors in and out of GPU
if torch.cuda.is_available():
    device = torch.device("cuda")          # a CUDA device object
    y = torch.ones_like(x, device=device)  # directly create a tensor on GPU
    x = x.to(device)                       # or just use strings ``.to("cuda")``
    z = x + y
    print(z)
    print(z.to("cpu", torch.double))       # ``.to`` can also change dtype together!

tensor(8, device='cuda:0')
tensor(8., dtype=torch.float64)

更多内容参考：我的github: https://github.com/XNoteW/Studying/tree/master/PyTorch_beginner