关于神经网络输入输出的计算

简单记个笔记

为什么网络模型有固定的输入维度呢？

计算公式

# 写网络架构：两种方法
import torch
from torch import nn
from torch.nn import Conv2d,MaxPool2d,Flatten,Linear,Sequential
#  pytorch的nn.module 的时候从使用说明上可以知道其标准输入为 [B, C, H, W]
#  方法1  直接搭建
class MyModule(nn.Module):
    def __init__(self):
        # super(MyModule, self).__init__()
        super().__init__()
        self.conv1 = nn.Conv2d(3,32,5,padding=2)
        self.maxpool1 = nn.MaxPool2d(2)
        self.conv2 = nn.Conv2d(32,32,5,padding=2)
        self.maxpool2 = nn.MaxPool2d(2)
        self.conv3 = nn.Conv2d(32, 64, 5, padding= 2)
        self.maxpool3 = nn.MaxPool2d(2)
        self.flatten = nn.Flatten()
        self.Linear1 = nn.Linear(1024,64)
        self.Linear2 = nn.Linear(64, 10)


    def forward(self,x):
        x = self.conv1(x)
        x = self.maxpool1(x)
        x = self.conv2(x)
        x = self.maxpool2(x)
        x = self.conv3(x)
        x = self.maxpool3(x)
        x = self.flatten(x)
        x = self.Linear1(x)
        x = self.Linear2(x)
        return x

#  方法2  Sequantial

class MyModule2(nn.Module):
    def __init__(self):
        super().__init__()
        self.model1 = Sequential(
        Conv2d(3,32,5,padding=2),
        MaxPool2d(2),
        Conv2d(32,32,5,padding=2),
        nn.MaxPool2d(2),
        Conv2d(32, 64, 5, padding= 2),
        MaxPool2d(2),
        Flatten(),
        Linear(1024,64),
        Linear(64, 10)
        )

    def forward(self, x):
        x = self.model1(x)
        return x

mymodule = MyModule()
mymodule2 = MyModule2()
print(mymodule)  #打印网络

# 测试网络
input = torch.ones((64,3,32,32))
print(input)
output = mymodule2(input)   ## 出错 output  是none
print(output.shape)
print("over")

输出

MyModule(
  (conv1): Conv2d(3, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (maxpool1): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
  (conv2): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (maxpool2): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
  (conv3): Conv2d(32, 64, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (maxpool3): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
  (flatten): Flatten(start_dim=1, end_dim=-1)
  (Linear1): Linear(in_features=1024, out_features=64, bias=True)
  (Linear2): Linear(in_features=64, out_features=10, bias=True)
)