如何使用PyTorch torch.max（）

素颜马尾好姑娘i 2023-02-28 08:39 9阅读 0赞

In this article, we’ll take a look at using the PyTorch **torch.max()** function.

在本文中，我们将介绍如何使用PyTorch **torch.max（）**函数。

As you may expect, this is a very simple function, but interestingly, it has more than you imagine.

如您所料，这是一个非常简单的功能，但有趣的是，它具有的功能超出了您的想象。

Let’s take a look at using this function, using some simple examples.

让我们使用一些简单的示例来看看如何使用此功能。

**NOTE**: At the time of writing, the PyTorch version used is **PyTorch 1.5.0**

**注意** ：在撰写本文时，使用的PyTorch版本是**PyTorch 1.5.0**

--------------------

## PyTorch torch.max（）–基本语法 **(****PyTorch torch.max() – Basic Syntax****)** ##

To use PyTorch `torch.max()`, first import `torch`.

要使用PyTorch `torch.max()` ，请首先导入`torch` 。

import torch

Now, this function returns the maximum among the elements in the Tensor.

现在，此函数返回张量中元素之间的最大值。

### PyTorch torch.max（）的默认行为 **(****Default Behavior of PyTorch torch.max()****)** ###

The default behavior is to return a single element and an index, corresponding to the global maximum element.

默认行为是返回单个元素和对应于全局最大元素的索引。

max_element = torch.max(input_tensor)

Here is an example:

这是一个例子：

p = torch.randn([2, 3])
    print(p)
    max_element = torch.max(p)
    print(max_element)

**Output**

**输出量**

tensor([[-0.0665,  2.7976,  0.9753],
            [ 0.0688, -1.0376,  1.4443]])
    tensor(2.7976)

Indeed, this gives us the global maximum element in the Tensor!

确实，这使我们在张量中具有全局最大元素！

--------------------

### 沿尺寸使用torch.max（） **(****Use torch.max() along a dimension****)** ###

However, you may wish to get the maximum along a particular dimension, as a [Tensor][], instead of a single element.

但是，您可能希望沿特定尺寸获得最大值，即[Tensor][]而不是单个元素。

To specify the dimension (**axis** – in `numpy`), there is another optional keyword argument, called `dim`

要指定尺寸（ **axis** –在`numpy` ），还有另一个可选的关键字参数，称为`dim`

This represents the direction that we take for the maximum.

这代表了我们追求最大的方向。

This returns a tuple, `max_elements` and `max_indices`.

这将返回一个元组`max_elements`和`max_indices` 。

*  `max_elements` \-> All the maximum elements of the Tensor.
    
    `max_elements` >张量的所有最大元素。

*  `max_indices` \-> Indices corresponding to the maximum elements.
    
    `max_indices` >对应于最大元素的索引。

max_elements, max_indices = torch.max(input_tensor, dim)

This will return a Tensor, which has the maximum elements along the dimension `dim`.

这将返回一个Tensor，其在`dim`维度上具有最大元素。

Let’s now look at some examples.

现在让我们看一些示例。

p = torch.randn([2, 3])
    print(p)
    
    # Get the maximum along dim = 0 (axis = 0)
    max_elements, max_idxs = torch.max(p, dim=0)
    print(max_elements)
    print(max_idxs)

**Output**

**输出量**

tensor([[-0.0665,  2.7976,  0.9753],
            [ 0.0688, -1.0376,  1.4443]])
    tensor([0.0688, 2.7976, 1.4443])
    tensor([1, 0, 1])

As you can see, we find the maximum along the dimension 0 (maximum along columns).

如您所见，我们在维度0上找到最大值（在列上找到最大值）。

Also, we get the indices corresponding to the elements. For example,`0.0688` has the index `1` along column 0

同样，我们获得与元素相对应的索引。 例如， `0.0688`在第0列的索引为`1`

Similarly, if you want to find the maximum along the rows, use `dim=1`.

同样，如果要在行中查找最大值，请使用`dim=1` 。

# Get the maximum along dim = 1 (axis = 1)
    max_elements, max_idxs = torch.max(p, dim=1)
    print(max_elements)
    print(max_idxs)

**Output**

**输出量**

tensor([2.7976, 1.4443])
    tensor([1, 2])

Indeed, we get the maximum elements along the row, and the corresponding index (along the row).

确实，我们获得了沿着该行的最大元素以及相应的索引（沿着该行）。

--------------------

## 使用torch.max（）进行比较 **(****Using torch.max() for comparison****)** ##

We can also use `torch.max()` to get the maximum values between two Tensors.

我们还可以使用`torch.max()`获得两个张量之间的最大值。

output_tensor = torch.max(a, b)

Here, `a` and `b` must have the same dimensions, or must be “broadcastable” Tensors.

在此， `a`和`b`必须具有相同的尺寸，或者必须是“可广播的”张量。

Here is a simple example to compare two Tensors having the same dimensions.

这是一个比较两个具有相同尺寸的张量的简单示例。

p = torch.randn([2, 3])
    q = torch.randn([2, 3])
    
    print("p =", p)
    print("q =",q)
    
    # Compare elements of p and q and get the maximum
    max_elements = torch.max(p, q)
    
    print(max_elements)

**Output**

**输出量**

p = tensor([[-0.0665,  2.7976,  0.9753],
            [ 0.0688, -1.0376,  1.4443]])
    q = tensor([[-0.0678,  0.2042,  0.8254],
            [-0.1530,  0.0581, -0.3694]])
    tensor([[-0.0665,  2.7976,  0.9753],
            [ 0.0688,  0.0581,  1.4443]])

Indeed, we get the output tensor having maximum elements between `p` and `q`.

实际上，我们得到的输出张量具有在`p`和`q`之间的最大元素。

--------------------

## 结论 **(****Conclusion****)** ##

In this article, we learned about using the torch.max() function, to find out the maximum element of a Tensor.

在本文中，我们学习了如何使用torch.max（）函数来查找张量的最大元素。

We also used this function to compare two tensors and get the maximum among them.

我们还使用此函数比较两个张量，并在其中得到最大值。

For similar articles, do go through our content on our [PyTorch tutorials][]! Stay tuned for more!

对于类似的文章，请在我们的[PyTorch教程中][PyTorch tutorials]浏览我们的内容！ 敬请期待更多！

## 参考资料 **(****References****)** ##

*  [PyTorch Official Documentation][] on torch.max()
    
    关于torch.max（）的[PyTorch官方文档][PyTorch Official Documentation]

--------------------

> 翻译自: [https://www.journaldev.com/39463/pytorch-torch-max][https_www.journaldev.com_39463_pytorch-torch-max]

[Tensor]: https://www.journaldev.com/37948/pytorch-tensor
[PyTorch tutorials]: https://www.journaldev.com/pytorch
[PyTorch Official Documentation]: https://pytorch.org/docs/stable/torch.html#torch.max
[https_www.journaldev.com_39463_pytorch-torch-max]: https://www.journaldev.com/39463/pytorch-torch-max