[PyTorch][chapter 41][卷积网络实战-LeNet5]

前言

这里结合前面学过的LeNet5 模型，总结一下卷积网络搭建，训练的整个流程

目录：

1： LeNet-5

2: 卷积网络总体流程

3：代码

一 LeNet-5

LeNet-5是一个经典的深度卷积神经网络，由Yann LeCun在1998年提出，旨在解决手写数字识别问题，被认为是卷积神经网络的开创性工作之一。该网络是第一个被广泛应用于数字图像识别的神经网络之一，也是深度学习领域的里程碑之一

层	参数	输出shape
输入层		[batch,channel,32,32]
C1(卷积层)	6@5x5 卷积核 ,stride=1 ,padding=0	[batch,6,28,28]
S2（池化层）	kernel_size=2,stride=2,padding=0	[batch,6,14,14]
C3(卷积层)	16@5x5 卷积核，stride=1,padding=0	[batch,16,10,10]
S4（池化层）	kernel_size=2,stride=2,padding=0	[batch,16,5,5]
C5(卷积层)	120@5x5卷积核,stride=1，padding=0	[batch,120,1,1]
F6层-全连接层	nn.Linear(in_features=120, out_features=84)	[batch,120]
Output层-全连接层	nn.Linear(in_features=120, out_features=10)	[batch,10]

二卷积网络的总体流程

2.1、nn.Module建立神经网络模型
model = LeNet5()

2.2、建立此网络的可学习的参数,以及更新规则
optimizer = optim.Adam(model.Parameters(), lr=1e-3)

梯度更新的公式

2.3、构建损失函数

损失函数模型
criteon = nn.CrossEntropyLoss()

2.4 前向传播

logits = model(x)

根据现有的权重系数,预测输出

2.5 反向传播

optimizer.zero_grad() #先将梯度归零w_grad
loss.backward() #反向传播计算得到每个参数的梯度值w_grad

通过当前的loss ，计算梯度

2.6 利用optim 更新权重系数

optimizer.step() #更新权重系数W

利用优化器更新权重系数

三代码

# -*- coding: utf-8 -*-
"""
Created on Thu Jun 15 14:32:54 2023@author: chengxf2
"""
import torch
from torch import nn
from torch.nn import functional as F 
from torchvision import datasets
from torchvision import transforms
from torch.utils.data import DataLoader
import torch.optim as optim 
import sslclass  LeNet5(nn.Module):"""for cifar10 dataset"""def __init__(self):super(LeNet5, self).__init__()self.conv_unit = nn.Sequential(#卷积层1 x:[b,3,32,32] => [b,6, 30,30]nn.Conv2d(in_channels=3, out_channels=6, kernel_size=5,stride=1,padding=0),#池化层1nn.MaxPool2d(kernel_size=2,stride=2, padding =0),#卷积层2  nn.Conv2d(in_channels=6, out_channels=16, kernel_size=5,stride=1, padding=0),#池化层2nn.MaxPool2d(kernel_size=2,stride=2, padding =0)#x:[b,16,5,5])self.flatten = nn.Flatten(start_dim =1, end_dim = -1)self.fc_unit = nn.Sequential(nn.Linear(in_features=16*5*5, out_features=120),nn.ReLU(),nn.Linear(in_features=120, out_features=84),nn.ReLU(),nn.Linear(in_features=84, out_features=10))def forward(self, x):'''Parameters----------x : [batch,channel=3, width=32, height=32].Returns-------out : DESCRIPTION.'''#[b,3,32,32] =>[b,16,5,5]out = self.conv_unit(x)#print("\n 卷积层输出 ：",out.shape)#[b,16,5,5]=>[b,16*5*5]out = self.flatten(out)#print("\n flatten层输出 ：",out.shape)#[b,400]=>[b,10]out = self.fc_unit(out)#print("\n 全连接层输出 ：",out.shape)#pred = F.softmax(out,dim=1)return outdef train():x = torch.randn(8,3,32,32)net = LeNet5()out = net(x)print(out.shape)def main():batchSize =32 maxIter = 10dataset_trans = transforms.Compose([transforms.ToTensor(),transforms.Resize((32,32))]) imgDir='./data'print("\n ---beg----")cifar_train = datasets.CIFAR10(root= imgDir,train=True, transform= dataset_trans,download =False) cifar_test =  datasets.CIFAR10(root= imgDir,train=False,transform= dataset_trans,download =False) train_data = DataLoader(cifar_train, batch_size=batchSize,shuffle=True)test_data = DataLoader(cifar_test, batch_size=batchSize,shuffle=True)print("\n --download finsh---")device = torch.device('cuda')# DataLoader迭代产生训练数据提供给模型 model = LeNet5().to(device)criteon = nn.CrossEntropyLoss() #前向传播计算lossoptimizer = optim.Adam(model.parameters(), lr=1e-3, betas=(0.9, 0.999)) #反向传播for epoch in range(maxIter):for batchindex,(x,label) in enumerate(train_data):#x: [b,3,32,32]#label: [b]x,label = x.to(device),label.to(device)logits = model(x)loss = criteon(logits, label)#backpopoptimizer.zero_grad()loss.backward()optimizer.step() #更新梯度if batchindex%500 ==0:print('batchindex {}, loss {}'.format(batchindex, loss.item()))model.eval()total_correct =0.0total_num = 0.0with torch.no_grad():for batchindex,(x,label) in enumerate(test_data):x,label = x.to(device),label.to(device)logits = model(x)pred = logits.argmax(dim=1)total_correct += torch.eq(pred, label).float().sum()total_num += x.size(0)acc = total_correct/total_numprint('\n epoch: {} ,acc: {}  total_num: {}'.format(epoch, acc, total_num))if __name__ == "__main__":main()

因为不是灰度图，训练10轮，acc 只有 epoch: 9 ,acc: 0.6310999989509583 total_num: 10000.0

可以把卷积核调整小一点

参考：

https://mp.csdn.net/mp_blog/creation/editor/131209651

课时79 卷积神经网络训练_哔哩哔哩_bilibili

课时77 卷积神经网络实战-1_哔哩哔哩_bilibili