pytorch入门

This tutorial aims to familiarize you with the concept of tensors in PyTorch and introduce you to the operations involving tensors in PyTorch. The Pytorch module works with data structures called tensors, which are much similar to those of Tensorflow. Pytorch however, doesn’t require you to define the entire computational graph a priori. This makes Pytorch much easier to debug and understand.

本教程旨在使您熟悉PyTorch中的张量的概念，并向您介绍PyTorch中涉及张量的操作。 Pytorch模块使用称为张量的数据结构，与Tensorflow的数据结构非常相似。 但是，Pytorch不需要先验地定义整个计算图。 这使得Pytorch易于调试和理解。

Pytorch中的张量 (Tensors in Pytorch)

Tensors are multi-dimensional structures similar to those occurring in NumPy module. PyTorch allows you to define and manipulate tensors in a similar manner to NumPy and also convert NumPy tensors to PyTorch and vice-versa.

张量是类似于NumPy模块中出现的多维结构。 PyTorch允许您以类似于NumPy的方式定义和操纵张量，并且还可以将NumPy张量转换为PyTorch，反之亦然。

PyTorch resides in the torch module. You should be able to run the following code and obtain the version of PyTorch once you finished the installation following .

PyTorch驻留在割炬模块中。 按照完成安装后，您应该能够运行以下代码并获取PyTorch的版本。

import torchfrom __future__ import print_functiontorch.version.__version__

Output:

输出：

'1.4.0'

Let us define our first tensor. Using the torch.tensor() method is one of the many ways to do this.

让我们定义第一个张量。 使用torch.tensor（）方法是执行此操作的多种方法之一。

x=torch.tensor([[2,3,4],[3,4,5]])x

Output:

输出：

tensor([[2, 3, 4],        [3, 4, 5]])

PyTorch has an is_tensor() method that checks whether a variable is a tensor or not.

PyTorch具有is_tensor（）方法，该方法检查变量是否为张量。

#Define an array of numbers.x=[10,20,30,40,50]#Check if x is a tensortorch.is_tensor(x)

Output:

输出：

False

To convert the array x into a tensor, we need to do the following.

要将数组x转换为张量，我们需要执行以下操作。

import numpy as nparr=np.array(x) # creating a numpy array from the list we defined earlierc=torch.from_numpy(arr) #create a tensor from the arraytorch.is_tensor(c)

Output:

输出：

True

Other methods of creating tensors are as follows:

创建张量的其他方法如下：

#Create a tensor of random normal numbers using randn() functiony=torch.randn(3, 3)#Create a tensor of zeros using torch.zeros()a=torch.zeros(2,2)#Create an identity tensor using torch.eye()b=torch.eye(3,4)#torch.linspace() - returns points within a given range in a linear space.lin = torch.linspace(2,10,steps=25)#torch.logspace() - returns points in a logarithmic spacelog = torch.logspace(start=-10,end=10,steps=10)#torch.rand() - returns specified number of random numbers within the # interval :math:`[0, 1)`random = torch.rand(2, 3)#random permutation of values between 0 to 10perm = torch.randperm(10) #items between 2 and 10, equally spaced by 2. If the last parameter is # ignored, step size will be 1.seq = torch.arange(2,10,2)

Now let us examine what values are stored in each of the tensors above.

现在让我们检查一下上面每个张量中存储了哪些值。

print(y)print(a)print(b)print(lin)print(log)print(random)print(perm)print(seq)

Output:

输出：

tensor([[ 0.9039,  0.6291,  1.0795],        [ 0.1586,  2.1939, -0.4900],        [-0.1909, -0.7503,  1.9355]])tensor([[0., 0.],        [0., 0.]])tensor([[1., 0., 0., 0.],        [0., 1., 0., 0.],        [0., 0., 1., 0.]])tensor([ 2.0000,  2.3333,  2.6667,  3.0000,  3.3333,  3.6667,  4.0000,  4.3333,         4.6667,  5.0000,  5.3333,  5.6667,  6.0000,  6.3333,  6.6667,  7.0000,         7.3333,  7.6667,  8.0000,  8.3333,  8.6667,  9.0000,  9.3333,  9.6667,        10.0000])tensor([1.0000e-10, 1.6681e-08, 2.7826e-06, 4.6416e-04, 7.7426e-02, 1.2916e+01,        2.1544e+03, 3.5938e+05, 5.9949e+07, 1.0000e+10])tensor([[ 0.8237,  0.5781,  0.6879],       [ 0.3816,  0.7249,  0.0998]])tensor([9, 1, 4, 5, 8, 2, 7, 6, 3, 0])tensor([2, 4, 6, 8])

重组张量 (Restructuring Tensors)

It helps a lot of times to be able to modify the shape and structure of tensors to suit our algorithm. PyTorch has several functions that add these flexibilities. First, let us define a tensor to illustrate this.

很多时候能够修改张量的形状和结构以适合我们的算法。 PyTorch具有增加这些灵活性的几种功能。 首先，让我们定义一个张量来说明这一点。

t1=torch.rand(3,4)t1

Output:

输出：

tensor([[0.0800, 0.4987, 0.3337, 0.5070],        [0.5671, 0.2567, 0.9441, 0.8524],        [0.5343, 0.8898, 0.9503, 0.3900]])

The following code transposes the tensor:

以下代码转置张量：

t1.t()

tensor([[0.0800, 0.5671, 0.5343],        [0.4987, 0.2567, 0.8898],        [0.3337, 0.9441, 0.9503],        [0.5070, 0.8524, 0.3900]])

Another alternative is using the transpose() function.

另一种选择是使用transpose（）函数。

#transpose needs dimension1 and dimension2 as attributes to transpose along the specified directions.t1.transpose(1,0)

tensor([[0.0800, 0.5671, 0.5343],        [0.4987, 0.2567, 0.8898],        [0.3337, 0.9441, 0.9503],        [0.5070, 0.8524, 0.3900]])

Reshaping tensors can be done in multiple ways:

重整张量可以通过多种方式完成：

• t1.reshape(a, b) will return a new tensor with the same data as t1 with size (a, b). This function copies the data to another part of memory, so it can be thought of as a clone.
  t1.reshape（a，b）将返回一个新的张量，该张量具有与t1相同的数据，大小为（a，b）。 此函数将数据复制到内存的另一部分，因此可以将其视为克隆。
• t1.resize_(a, b) returns the same tensor with a different shape, but some elements will be removed from the tensor if the new shape results in less number of elements than the original tensor. Note that these elements won’t be removed from the memory. However, if the new shape results in more elements than the tensor, those new elements will remain uninitialized in memory. Underscore shows that the method is performed in place.
  t1.resize_（a，b）返回具有不同形状的相同张量，但是如果新形状导致元素数量少于原始张量，则某些元素将从张量中删除。 请注意，这些元素不会从内存中删除。 但是，如果新形状产生的元素多于张量，则这些新元素将在内存中保持未初始化的状态。 下划线表明该方法是在原地执行的。
• t1.view(a, b) will return a new tensor with the same data as t1 with size (a, b).
  t1.view（a，b）将返回一个新的张量，该张量具有与t1相同的数据，大小为（a，b）。

All three methods work in the same way.

三种方法都以相同的方式工作。

ty=torch.randn(4,4)t2=ty.reshape(2,8)print(t2)

tensor([[-0.1995, -0.5073,  0.0820, -1.7935, -0.1631,  0.2086,  0.5033,  0.3686],        [ 0.0686,  0.0247, -0.4558, -0.1373,  1.1020,  0.6841,  1.1238, -0.4326]])

Pytorch中张量的数学运算 (Mathematical Operations on Tensors in Pytorch)

PyTorch offers a rich list of arithmetic operations that can be performed upon tensors for implementing any algorithm. Let us look at some of those in detail.

PyTorch提供了丰富的算术运算列表，可在张量上执行这些算术运算以实现任何算法。 让我们详细了解其中一些。

张量的加法 (Addition of tensors)

Tensor addition can be performed using torch.add() function.

张量加法可以使用torch.add()函数执行。

t1 = torch.tensor([2,3,4,5])t2 = torch.tensor([1,5,9,8])#Adds t1 and t2 and displays the result on consoletorch.add(t1,t2)#Adds t1 to t2 and stores the result in t1t1.add_(t2)#Define a new empty tensort3=torch.tensor(4)#Add t1 and t2 and store the result in t3torch.add(t1,t2, out= t3)print(t1)print(t3)

tensor([ 3,  8, 13, 13])tensor([ 4, 13, 22, 21])

A scalar can be added to every element of tensor in the following manner.

可以按以下方式将标量添加到张量的每个元素。

torch.add(t1,5)

tensor([8, 13, 18, 18])

张量的乘法 (Multiplication of tensors)

The function torch.mul() performs the element-wise multiplication of two tensors.

函数torch.mul()执行两个张量的按元素乘法。

torch.mul(t1,t2)

tensor([  3,  40, 117, 104])

矩阵乘法 (Matrix Multiplication)

Matrix and vector multiplication are supported by PyTorch using the torch.mm(matrix,matrix) and torch.mv(matrix,vector) functions.

PyTorch使用torch.mm(matrix,matrix)和torch.mv(matrix,vector)函数支持矩阵和向量乘法。

#Define a vectorvec = torch.randn(4)#Define a matrixmat = torch.randn(3,4)print(vec)print(mat)

tensor([ 0.4888,  0.9948, -0.5621, -0.8673])tensor([[-0.8077,  0.9913, -0.7615, -1.4975],        [-0.8250,  0.9404,  0.3022, -0.1274],        [-1.2982,  0.3702,  0.5074,  1.4800]])

torch.mv(mat,vec)

tensor([ 2.3182,  0.4729, -1.8350])

Similarly, matrix-matrix multiplication can be done using torch.mm() function.

同样，可以使用torch.mm()函数完成矩阵与矩阵的乘法。

mat1 = torch.tensor([[2,3],[4,5]])mat2 = torch.tensor([[4,5],[6,7]])torch.mm(mat1,mat2)

tensor([[26, 31],        [46, 55]])

结论 (Conclusion)

We’ve covered the basic working of tensors within PyTorch today. We’ll continue to work with the PyTorch module in the upcoming tutorials and cover further topics within this module. For now, I hope you’ve understood the concept and the basics of the module really well. If you have any questions related to the module, do let us know in the comments below.

今天，我们已经介绍了PyTorch中张量的基本工作。 我们将在接下来的教程中继续使用PyTorch模块，并在该模块中介绍更多主题。 到目前为止，我希望您真的很了解该模块的概念和基础。 如果您对模块有任何疑问，请在下面的评论中告诉我们。

翻译自:

pytorch入门