torch.nn.Module.extra_repr()

参考链接: torch.nn.Module.extra_repr()

PyTorch的源代码:

原文及翻译:

extra_repr()
方法: extra_repr()
    Set the extra representation of the module
    设置模块的额外表示信息.
    To print customized extra information, you should reimplement 
    this method in your own modules. Both single-line and multi-line 
    strings are acceptable.
    为了能够打印用户定制化的额外信息,你需要在你的神经网络模块中重新实现这
    个方法. 单行字符串或多行字符串都可以用在这个函数中.

实验代码展示:

import torch 
import torch.nn as nn
torch.manual_seed(seed=20200910)
class Model(torch.nn.Module):
    def __init__(self):
        super(Model,self).__init__()
        self.conv1=torch.nn.Sequential(  # 输入torch.Size([64, 1, 28, 28])
                torch.nn.Conv2d(1,64,kernel_size=3,stride=1,padding=1),
                torch.nn.ReLU(),  # 输出torch.Size([64, 64, 28, 28])
                torch.nn.Conv2d(64,128,kernel_size=3,stride=1,padding=1),  # 输出torch.Size([64, 128, 28, 28])
                torch.nn.ReLU(),
                torch.nn.MaxPool2d(stride=2,kernel_size=2)  # 输出torch.Size([64, 128, 14, 14])
        )

        self.dense=torch.nn.Sequential(  # 输入torch.Size([64, 14*14*128])
                    torch.nn.Linear(14*14*128,1024),  # 输出torch.Size([64, 1024])
                    torch.nn.ReLU(),
                    torch.nn.Dropout(p=0.5),
                    torch.nn.Linear(1024,10)  # 输出torch.Size([64, 10])        
        )
        self.layer4cxq1 = torch.nn.Conv2d(2,33,4,4)
        self.layer4cxq2 = torch.nn.ReLU()
        self.layer4cxq3 = torch.nn.MaxPool2d(stride=2,kernel_size=2)
        self.layer4cxq4 = torch.nn.Linear(14*14*128,1024)
        self.layer4cxq5 = torch.nn.Dropout(p=0.8)
        self.attribute4cxq = nn.Parameter(torch.tensor(20200910.0))
        self.attribute4lzq = nn.Parameter(torch.tensor([2.0,3.0,4.0,5.0]))    
        self.attribute4hh = nn.Parameter(torch.randn(3,4,5,6))
        self.attribute4wyf = nn.Parameter(torch.randn(7,8,9,10))

    def forward(self,x):  # torch.Size([64, 1, 28, 28])
        x = self.conv1(x)  # 输出torch.Size([64, 128, 14, 14])
        x = x.view(-1,14*14*128)  # torch.Size([64, 14*14*128])
        x = self.dense(x)  # 输出torch.Size([64, 10])
        return x

print('cuda(GPU)是否可用:',torch.cuda.is_available())
print('torch的版本:',torch.__version__)

model = Model() #.cuda()
print('用户定制前'.center(100,"-"))

print("打印模型".center(100,"-"))
print(model)

print('调用__repr__(self)方法'.center(100,"-"))
print(model.__repr__())
print('调用extra_repr(self)方法'.center(100,"-"))
print(model.extra_repr())



class Model4cxq(torch.nn.Module):
    def __init__(self):
        super(Model4cxq,self).__init__()
        self.conv1=torch.nn.Sequential(  # 输入torch.Size([64, 1, 28, 28])
                torch.nn.Conv2d(1,64,kernel_size=3,stride=1,padding=1),
                torch.nn.ReLU(),  # 输出torch.Size([64, 64, 28, 28])
                torch.nn.Conv2d(64,128,kernel_size=3,stride=1,padding=1),  # 输出torch.Size([64, 128, 28, 28])
                torch.nn.ReLU(),
                torch.nn.MaxPool2d(stride=2,kernel_size=2)  # 输出torch.Size([64, 128, 14, 14])
        )

        self.dense=torch.nn.Sequential(  # 输入torch.Size([64, 14*14*128])
                    torch.nn.Linear(14*14*128,1024),  # 输出torch.Size([64, 1024])
                    torch.nn.ReLU(),
                    torch.nn.Dropout(p=0.5),
                    torch.nn.Linear(1024,10)  # 输出torch.Size([64, 10])        
        )
        self.layer4cxq1 = torch.nn.Conv2d(2,33,4,4)
        self.layer4cxq2 = torch.nn.ReLU()
        self.layer4cxq3 = torch.nn.MaxPool2d(stride=2,kernel_size=2)
        self.layer4cxq4 = torch.nn.Linear(14*14*128,1024)
        self.layer4cxq5 = torch.nn.Dropout(p=0.8)
        self.attribute4cxq = nn.Parameter(torch.tensor(20200910.0))
        self.attribute4lzq = nn.Parameter(torch.tensor([2.0,3.0,4.0,5.0]))    
        self.attribute4hh = nn.Parameter(torch.randn(3,4,5,6))
        self.attribute4wyf = nn.Parameter(torch.randn(7,8,9,10))

    def forward(self,x):  # torch.Size([64, 1, 28, 28])
        x = self.conv1(x)  # 输出torch.Size([64, 128, 14, 14])
        x = x.view(-1,14*14*128)  # torch.Size([64, 14*14*128])
        x = self.dense(x)  # 输出torch.Size([64, 10])
        return x
    
    def extra_repr(self):
        # print('extra_repr方法正在被调用...')
        return '我是用户自定义的神经网络模块...'

print('用户定制后'.center(100,"-"))
model4cxq = Model4cxq() #.cuda()
print("打印模型".center(100,"-"))
print(model4cxq)

print('调用__repr__(self)方法'.center(100,"-"))
print(model4cxq.__repr__())
print('调用extra_repr(self)方法'.center(100,"-"))
print(model4cxq.extra_repr())

控制台输出结果:

Windows PowerShell
版权所有 (C) Microsoft Corporation。保留所有权利。

尝试新的跨平台 PowerShell https://aka.ms/pscore6

加载个人及系统配置文件用了 918 毫秒。
(base) PS C:\Users\chenxuqi\Desktop\News4cxq\test4cxq> conda activate ssd4pytorch1_2_0
(ssd4pytorch1_2_0) PS C:\Users\chenxuqi\Desktop\News4cxq\test4cxq>  & 'D:\Anaconda3\envs\ssd4pytorch1_2_0\python.exe' 'c:\Users\chenxuqi\.vscode\extensions\ms-python.python-2020.12.424452561\pythonFiles\lib\python\debugpy\launcher' '65434' '--' 'c:\Users\chenxuqi\Desktop\News4cxq\test4cxq\test31.py'
cuda(GPU)是否可用: True
torch的版本: 1.2.0+cu92
-----------------------------------------------用户定制前------------------------------------------------
------------------------------------------------打印模型------------------------------------------------
Model(
  (conv1): Sequential(
    (0): Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (1): ReLU()
    (2): Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (3): ReLU()
    (4): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
  )
  (dense): Sequential(
    (0): Linear(in_features=25088, out_features=1024, bias=True)
    (1): ReLU()
    (2): Dropout(p=0.5, inplace=False)
    (3): Linear(in_features=1024, out_features=10, bias=True)
  )
  (layer4cxq1): Conv2d(2, 33, kernel_size=(4, 4), stride=(4, 4))
  (layer4cxq2): ReLU()
  (layer4cxq3): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
  (layer4cxq4): Linear(in_features=25088, out_features=1024, bias=True)
  (layer4cxq5): Dropout(p=0.8, inplace=False)
)
-----------------------------------------调用__repr__(self)方法-----------------------------------------
Model(
  (conv1): Sequential(
    (0): Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (1): ReLU()
    (2): Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (3): ReLU()
    (4): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
  )
  (dense): Sequential(
    (0): Linear(in_features=25088, out_features=1024, bias=True)
    (1): ReLU()
    (2): Dropout(p=0.5, inplace=False)
    (3): Linear(in_features=1024, out_features=10, bias=True)
  )
  (layer4cxq1): Conv2d(2, 33, kernel_size=(4, 4), stride=(4, 4))
  (layer4cxq2): ReLU()
  (layer4cxq3): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
  (layer4cxq4): Linear(in_features=25088, out_features=1024, bias=True)
  (layer4cxq5): Dropout(p=0.8, inplace=False)
)
----------------------------------------调用extra_repr(self)方法----------------------------------------

-----------------------------------------------用户定制后------------------------------------------------
------------------------------------------------打印模型------------------------------------------------
Model4cxq(
  我是用户自定义的神经网络模块...
  (conv1): Sequential(
    (0): Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (1): ReLU()
    (2): Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (3): ReLU()
    (4): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
  )
  (dense): Sequential(
    (0): Linear(in_features=25088, out_features=1024, bias=True)
    (1): ReLU()
    (2): Dropout(p=0.5, inplace=False)
    (3): Linear(in_features=1024, out_features=10, bias=True)
  )
  (layer4cxq1): Conv2d(2, 33, kernel_size=(4, 4), stride=(4, 4))
  (layer4cxq2): ReLU()
  (layer4cxq3): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
  (layer4cxq4): Linear(in_features=25088, out_features=1024, bias=True)
  (layer4cxq5): Dropout(p=0.8, inplace=False)
)
-----------------------------------------调用__repr__(self)方法-----------------------------------------
Model4cxq(
  我是用户自定义的神经网络模块...
  (conv1): Sequential(
    (0): Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (1): ReLU()
    (2): Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (3): ReLU()
    (4): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
  )
  (dense): Sequential(
    (0): Linear(in_features=25088, out_features=1024, bias=True)
    (1): ReLU()
    (2): Dropout(p=0.5, inplace=False)
    (3): Linear(in_features=1024, out_features=10, bias=True)
  )
  (layer4cxq1): Conv2d(2, 33, kernel_size=(4, 4), stride=(4, 4))
  (layer4cxq2): ReLU()
  (layer4cxq3): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
  (layer4cxq4): Linear(in_features=25088, out_features=1024, bias=True)
  (layer4cxq5): Dropout(p=0.8, inplace=False)
)
----------------------------------------调用extra_repr(self)方法----------------------------------------
我是用户自定义的神经网络模块...
(ssd4pytorch1_2_0) PS C:\Users\chenxuqi\Desktop\News4cxq\test4cxq>