Basic skeleton of neural network nn Use of moudle

Contains Official documents
The basic skeleton of neural network -nn.Moudle Use official documents of
According to the example of official documents ：

import torch.nn as nn
import torch.nn.functional as F

class Model(nn.Module):
    def __init__(self):
        super().__init__()
        self.conv1 = nn.Conv2d(1, 20, 5)
        self.conv2 = nn.Conv2d(20, 20, 5)

    def forward(self, x):
        x = F.relu(self.conv1(x))
        return F.relu(self.conv2(x))

step ： Use the basic skeleton of neural network -nn.Moudle, It can be divided into three steps .

• Create a class inheritance nn.Module
• Inherit nn.Module The initialization of plus their own initialization
• rewrite forword Method

Explanation of the code in this part of the official document ：

def forward(self, x):
        x = F.relu(self.conv1(x))
        return F.relu(self.conv2(x))

Look at the picture , Very vivid .

nn.Moudle Examples of use ：

import torch
from torch import nn

#  Create a class inheritance nn.Module
class Tudui(nn.Module):
	#  Inherit nn.Module The initialization 
    def __init__(self):
        super().__init__()
	#  rewrite forword Method 
    def forward(self,input):
        output = input+1
        return output

#  Create a class object 
obj = Tudui()
x = torch.tensor(1.0)
#  Pass parameters into the class object and receive the results 
output = obj(x)
#  Output results 
print(output)

Code run results ：