PyTorch softmax - torch.nn - torch.nn.functional

「爱情、让人受尽委屈。」 2023-02-20 02:20 146阅读 0赞

#  PyTorch `softmax` \- `torch.nn` \- `torch.nn.functional` #

**PyTorch documentation**  
[https://pytorch.org/docs/stable/index.html][https_pytorch.org_docs_stable_index.html]

## 0. `softmax` \- `torch.nn` \- `torch.nn.functional` ##

*  `torch.nn.functional.softmax` (Python function, in `torch.nn.functional`)  
    定义的是一个函数。`torch.nn.functional` 中定义的是函数，由 `def function()` 定义，是一个固定的运算公式。
 *  `torch.nn.Softmax` (Python class, in `torch.nn`)  
    定义的是一个类。`torch.nn` 中定义的是类，以 `class xx` 来定义的，可以提取变化的学习参数。

`torch.nn.Softmax` 是 Module 类，在实例化类后会初始化运算所需要的参数。这些参数会在 forward 和 backward 之后根据 loss 进行更新，通常存放在定义模型的 `__init__()` 中。在 Module 类里的 `__call__` 实现了 `forward()` 函数的调用。

train 和 test 阶段运行方法一致时，尽量用 `torch.nn`，避免手动控制操作。

深度学习中权重需要不断更新，需要采用类的方式，以确保能在参数发生变化时仍能使用之前定好的运算步骤。如果模型有可学习的参数，应该使用 `torch.nn`。但是简单的计算不需要建类来做，所以使用 `torch.nn.functional` 定义函数即可。

<table> 
 <thead> 
  <tr> 
   <th>torch.nn.name</th> 
   <th>torch.nn.functional.name</th> 
  </tr> 
 </thead> 
 <tbody> 
  <tr> 
   <td>类</td> 
   <td>函数</td> 
  </tr> 
  <tr> 
   <td>结构中包含所需要初始化的参数。</td> 
   <td>在函数外定义并初始化相应参数，并作为参数传入。</td> 
  </tr> 
  <tr> 
   <td>在 <code>__init__()</code> 中实例化，并在 forward 中运算。</td> 
   <td>在 <code>__init__()</code> 中初始化相应参数，在 forward 中传入参数。</td> 
  </tr> 
 </tbody> 
</table>

## 1. `softmax` \- `torch.nn.functional.softmax` (Python function, in `torch.nn.functional`) ##

[https://pytorch.org/docs/stable/nn.functional.html][https_pytorch.org_docs_stable_nn.functional.html]

`torch.nn.functional.softmax(input, dim=None, _stacklevel=3, dtype=None)`

Applies a `softmax` function.  
应用 `softmax` 函数。

Softmax is defined as:

Softmax ( x i ) = e x p ( x i ) ∑ j e x p ( x j ) \\text\{Softmax\}(x\_\{i\}) = \\frac\{exp(x\_i)\}\{\\sum\_j exp(x\_j)\} Softmax(xi)=∑jexp(xj)exp(xi)

It is applied to all slices along dim, and will re-scale them so that the elements lie in the range `[0, 1]` and sum to `1`.  
它应用于 `dim` 上的所有切片, 并将对它们进行重新缩放, 使元素位于 `[0, 1]` 范围内，和为 1。

See `Softmax` for more details.  
[https://pytorch.org/docs/stable/nn.html\#torch.nn.Softmax][https_pytorch.org_docs_stable_nn.html_torch.nn.Softmax]

### 1.1 Parameters ###

`input (Tensor)` – input

`dim (int)` – A dimension along which `softmax` will be computed.  
`dtype (torch.dtype, optional)` – the desired data type of returned `tensor`. If specified, the input tensor is casted to `dtype` before the operation is performed. This is useful for preventing data type overflows. Default: `None`.  
返回 `tenosr` 的期望数据类型。如果指定了参数，输入张量在执行操作之前被转换为 `dtype`。这对于防止数据类型溢出非常有用。默认值：`None`。

This function doesn’t work directly with `NLLLoss`, which expects the `Log` to be computed between the `Softmax` and itself. Use `log_softmax` instead (it’s faster and has better numerical properties).  
此函数不能直接与 `NLLLoss` 一起使用，`NLLLoss` 希望在 `Softmax` 及其自身之间计算 `Log`。使用 `log_softmax` 来代替 (它更快，并且具有更好的数值属性)。

## 2. `softmax` \- `torch.nn.Softmax` (Python class, in `torch.nn`) ##

[https://pytorch.org/docs/stable/nn.html][https_pytorch.org_docs_stable_nn.html]

`CLASS torch.nn.Softmax(dim=None)`

Applies the `Softmax` function to an n-dimensional input Tensor rescaling them so that the elements of the n-dimensional output Tensor lie in the range `[0, 1]` and sum to 1.  
将 `Softmax` 函数应用于 n 维输入 Tensor，对其进行重新缩放，以使 n 维输出 Tensor 的元素位于 `[0, 1]` 范围内，且总和为 1。

Softmax is defined as:

Softmax ( x i ) = exp ⁡ ( x i ) ∑ j exp ⁡ ( x j ) \\text\{Softmax\}(x\_\{i\}) = \\frac\{\\exp(x\_i)\}\{\\sum\_j \\exp(x\_j)\} Softmax(xi)=∑jexp(xj)exp(xi)

### 2.1 Shape ###

Input: (`*`) where `*` means, any number of additional dimensions  
Output: (`*`), same shape as the input

### 2.2 Returns ###

a Tensor of the same dimension and shape as the input with values in the range `[0, 1]`.

### 2.3 Parameters ###

`dim (int)` – A dimension along which Softmax will be computed (so every slice along `dim` will sum to 1).  
用来计算 Softmax 的尺寸 (因此，沿 `dim` 的每个切片的总和为 1)。

This module doesn’t work directly with `NLLLoss`, which expects the `Log` to be computed between the `Softmax` and itself. Use `LogSoftmax` instead (it’s faster and has better numerical properties).

## 3. Examples ##

![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2NoZW5neXExMTY_size_16_color_FFFFFF_t_70_pic_center]

### 3.1 example ###

### 3.2 example ###

执行算子后，在 `dim=0` 维上的分布，`output_0[0][0][0]+ output_0[1][0][0] = 1`。

(pt-1.4_py-3.6) yongqiang@yongqiang:~$ python
    Python 3.6.10 |Anaconda, Inc.| (default, May  8 2020, 02:54:21)
    [GCC 7.3.0] on linux
    Type "help", "copyright", "credits" or "license" for more information.
    >>> import torch
    >>> import torch.nn.functional as F
    >>>
    >>> input = torch.randn(2, 3, 4)
    >>> input
    tensor([[[-0.3976,  0.4142, -0.5061, -0.4063],
             [-0.2401, -1.5699,  1.4867, -1.9940],
             [ 0.5525, -1.4140, -1.2408, -0.6638]],
    
            [[-1.7829,  0.1077,  0.8127, -2.8241],
             [ 1.4750,  0.5804,  1.1887, -0.6570],
             [ 0.2279,  0.9583, -1.9489, -0.5876]]])
    >>>
    >>> output_0 = F.softmax(input, dim=0)
    >>> output_0
    tensor([[[0.7999, 0.5760, 0.2110, 0.9182],
             [0.1525, 0.1043, 0.5740, 0.2080],
             [0.5805, 0.0853, 0.6700, 0.4810]],
    
            [[0.2001, 0.4240, 0.7890, 0.0818],
             [0.8475, 0.8957, 0.4260, 0.7920],
             [0.4195, 0.9147, 0.3300, 0.5190]]])
    >>>
    >>> output_1 = F.softmax(input, dim=1)
    >>> output_1
    tensor([[[0.2102, 0.7703, 0.1134, 0.5057],
             [0.2461, 0.1059, 0.8322, 0.1034],
             [0.5437, 0.1238, 0.0544, 0.3909]],
    
            [[0.0290, 0.2022, 0.3969, 0.0524],
             [0.7543, 0.3244, 0.5780, 0.4574],
             [0.2167, 0.4734, 0.0251, 0.4903]]])
    >>>
    >>> output_2 = F.softmax(input, dim=2)
    >>> output_2
    tensor([[[0.1945, 0.4381, 0.1745, 0.1928],
             [0.1416, 0.0375, 0.7964, 0.0245],
             [0.6239, 0.0873, 0.1038, 0.1849]],
    
            [[0.0468, 0.3098, 0.6269, 0.0165],
             [0.4389, 0.1794, 0.3296, 0.0521],
             [0.2753, 0.5716, 0.0312, 0.1218]]])
    >>>
    >>> exit()
    (pt-1.4_py-3.6) yongqiang@yongqiang:~$

### 3.3 example ###

`dim=0` 是张量的 0 轴，`dim=1` 是张量的 1 轴。

### 3.4 example ###

[https_pytorch.org_docs_stable_index.html]: https://pytorch.org/docs/stable/index.html
[https_pytorch.org_docs_stable_nn.functional.html]: https://pytorch.org/docs/stable/nn.functional.html
[https_pytorch.org_docs_stable_nn.html_torch.nn.Softmax]: https://pytorch.org/docs/stable/nn.html#torch.nn.Softmax
[https_pytorch.org_docs_stable_nn.html]: https://pytorch.org/docs/stable/nn.html
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2NoZW5neXExMTY_size_16_color_FFFFFF_t_70_pic_center]: https://img-blog.csdnimg.cn/20200622001242461.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2NoZW5neXExMTY=,size_16,color_FFFFFF,t_70#pic_center