（1）利用Netron查看网络实际情况
上图链接
python生成上图代码如下，其中GETVGGnet是搭建VGG网络的程序GETVGGnet.py，VGGnet是该程序中的搭建网络类。netron是需要pip安装的可视化库，注意do_constant_folding=False可以防止Netron中不显示Batchnorm2D层，禁用参数隐藏。
import torch
from torch.autograd import Variable
from GetVGGnet import VGGnet
import netron
net = VGGnet()
x = Variable(torch.FloatTensor(1,3,28,28))
y = net(x)
print(y.data.shape)
onnx_path = "./save_model/VGGnet.onnx"
torch.onnx.export(net, x, onnx_path,do_constant_folding=False)
print(net)
netron.start(onnx_path)
（2）VGG训练测试全过程
此次训练在CPU上进行，迭代次epoch = 10，迭代内轮次batch=300，训练集10000张，测试集2000张。
train loss和train corre分别代表损失和正确率，横轴是不同迭代下每一个伦次的loss&corre累加，一个迭代进行33个轮次，每个迭代最后一个伦次数据不足被网络舍弃，10个迭代总共320次。test loss和test corre是每个一个迭代下所有伦次的正确率平均值。根据图可以看出，训练和测试结果都较好。
训练的损失和正确率在波动，但总体趋势较好。
数据集大小可以在此处修改：
代码：cifar10_handle和GetVGGnet在上几篇文章有说明
#!/usr/bin/env python
# -*- coding:utf-8 -*-
"""
@author: 楠楠星球
@time: 2024/5/10 10:15
@file: VGGTrain.py-->test
@project: pythonProject
@# ------------------------------------------(one)--------------------------------------
@# ------------------------------------------(two)--------------------------------------
"""
import torch
import torch.nn as nn
from torch.utils.data import DataLoader
from GetVGGnet import VGGnet
from cifar10_handle import train_dataset,test_dataset
import matplotlib.pyplot as plt
epoch = 10 #迭代次数
learn_rate = 0.01 #初始学习率
net = VGGnet().to(device='cpu') #模型实例化
loss_fun = nn.CrossEntropyLoss() #调用损失函数
train_data_loder = DataLoader(dataset=train_dataset,
batch_size=300, #每一次迭代的调用的波次
shuffle=True, #这个波次是否打乱数据集
num_workers=4, # 线程数
drop_last=True) # 最后一个波次数据不足是否舍去
test_data_loder = DataLoader(dataset=test_dataset,
batch_size=300,
shuffle=False,
num_workers=4,
drop_last=True)
# optimizer = torch.optim.Adam(net.parameters(), lr=learn_rate)
optimizer = torch.optim.SGD(net.parameters(), lr=learn_rate, momentum=0.5) #优化器
# scheduler = torch.optim.lr_scheduler.StepLR(optijumizer, step_size=5, gamma=0.9) #step_size=1表示每迭代一次更新一下学习率
scheduler = torch.optim.lr_scheduler.ExponentialLR(optimizer, gamma=0.7) #学习率调整器
def train(epoch_num,train_net):
# ------------------------------------------()--------------------------------------
loss_base = []
corre_base = []
test_loss_base = []
test_corre_base =[]
for epoch in range(epoch_num):
# ------------------------------------------(TRAIN)--------------------------------------
train_net.train()
for i, data in enumerate(train_data_loder):
input_tensor, label = data
input_tensor = input_tensor.to(device='cpu')
label = label.to(device='cpu')
output_tensor = train_net(input_tensor)
loss = loss_fun(output_tensor, label)
optimizer.zero_grad()
loss.backward()
optimizer.step()
_, pred = torch.max(output_tensor.data, dim=1)
correct = pred.eq(label.data).cpu().sum()
print(f"训练中：第{epoch + 1}次迭代的小迭代{i}的损失率为：{1.00 * loss.item()},正确率为：{100.00 * correct / 300}")
loss_base.append(loss.item())
corre_base.append(100.00 * correct.item() / 300)
scheduler.step()
# ------------------------------------------(TEST)--------------------------------------
sum_test_loss = 0
sum_test_corre = 0
train_net.eval()
for i, test_data in enumerate(test_data_loder):
input_tensor, label = test_data
input_tensor = input_tensor.to(device='cpu')
label = label.to(device='cpu')
output_tensor = train_net(input_tensor)
loss = loss_fun(output_tensor, label)
_, pred = torch.max(output_tensor.data, dim=1)
correct = pred.eq(label.data).cpu().sum()
sum_test_loss += loss.item()
sum_test_corre += correct.item()
test_loss = sum_test_loss * 1.0 / len(test_data_loder)
test_corre = sum_test_corre * 100.0 / len(test_data_loder) / 300
test_loss_base.append(test_loss)
test_corre_base.append(test_corre)
print(f"测试中：当前迭代的测试集损失为：{test_loss},正确率为：{test_corre}")
return loss_base,corre_base,test_loss_base,test_corre_base
# ------------------------------------------()--------------------------------------
if __name__ == '__main__':
[train_loss,train_corre,test_loss,test_corr] = train(epoch,net)
fig, axes = plt.subplots(2, 2)
axes[0, 0].plot(list(range(1, len(train_loss)+1 )), train_loss,color ='r')
axes[0, 0].set_title('train loss')
axes[0, 1].plot(list(range(1, len(train_corre) + 1)), train_corre, color ='r')
axes[0, 1].set_title('train corre')
axes[1, 0].plot(list(range(1, len(test_loss) + 1)), test_loss,color ='r')
axes[1, 0].set_title('test loss')
axes[1, 1].plot(list(range(1, len(test_corr) + 1)), test_corr,color ='r')
axes[1, 1].set_title('test corre')
plt.show()
# torch.save(net.state_dict(), './save_model/example1.pt')
