pytorch系列教程(五)-保存网络结构及其参数

一、保存网络结构及其参数

torch.save(state, dir)
其中dir表示保存文件的绝对路径+保存文件名，如'/home/qinying/Desktop/modelpara.pth'
如果没有写绝对路径，就保存到当前路径下
torch.save(model,‘model.pth’) # 保存
model = torch.load(“model.pth”) # 加载

  

二、只保存参数

torch.save(model.state_dict(),“model.pth”) # 保存参数
model = model() # 代码中创建网络结构
params = torch.load(“model.pth”) # 加载参数
model.load_state_dict(params) # 应用到网络结构中

如果还想保存某一次训练采用的优化器、epochs等信息，可将这些信息组合起来构成一个字典，然后将字典保存起来：

state = {'model': model.state_dict(), 'optimizer': optimizer.state_dict(), 'epoch': epoch}
torch.save(state, “model.pth”)
model = model() # 代码中创建网络结构
checkpoint = torch.load(“model.pth”) 
model.load_state_dict(checkpoint['model'])
optimizer.load_state_dict(checkpoint['optimizer'])
epoch = checkpoint(['epoch'])

来个简单的例子
参考了Pytorch模型保存与加载，并在加载的模型基础上继续训练

#-*- coding:utf-8 -*-

'''本文件用于举例说明pytorch保存和加载文件的方法'''

__author__ = 'puxitong from UESTC'


import torch as torch
import torchvision as tv
import torch.nn as nn
import torch.optim as optim
import torch.nn.functional as F
import torchvision.transforms as transforms
from torchvision.transforms import ToPILImage
import torch.backends.cudnn as cudnn
import datetime
import argparse

# 参数声明
batch_size = 32
epochs = 10
WORKERS = 0   # dataloder线程数
test_flag = True  #测试标志，True时加载保存好的模型进行测试 
ROOT = '/home/pxt/pytorch/cifar'  # MNIST数据集保存路径
log_dir = '/home/pxt/pytorch/logs/cifar_model.pth'  # 模型保存路径

# 加载MNIST数据集
transform = tv.transforms.Compose([
        transforms.ToTensor(),
        transforms.Normalize([0.5, 0.5, 0.5], [0.5, 0.5, 0.5])])

train_data = tv.datasets.CIFAR10(root=ROOT, train=True, download=True, transform=transform)
test_data = tv.datasets.CIFAR10(root=ROOT, train=False, download=False, transform=transform)

train_load = torch.utils.data.DataLoader(train_data, batch_size=batch_size, shuffle=True, num_workers=WORKERS)
test_load = torch.utils.data.DataLoader(test_data, batch_size=batch_size, shuffle=False, num_workers=WORKERS)


# 构造模型
class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(3, 64, 3, padding=1)
        self.conv2 = nn.Conv2d(64, 128, 3, padding=1)
        self.conv3 = nn.Conv2d(128, 256, 3, padding=1)
        self.conv4 = nn.Conv2d(256, 256, 3, padding=1)
        self.pool = nn.MaxPool2d(2, 2)
        self.fc1 = nn.Linear(256 * 8 * 8, 1024)
        self.fc2 = nn.Linear(1024, 256)
        self.fc3 = nn.Linear(256, 10)
    
    
    def forward(self, x):
        x = F.relu(self.conv1(x))
        x = self.pool(F.relu(self.conv2(x)))
        x = F.relu(self.conv3(x))
        x = self.pool(F.relu(self.conv4(x)))
        x = x.view(-1, x.size()[1] * x.size()[2] * x.size()[3])
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        x = self.fc3(x)
        return x


model = Net().cuda()
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=0.01)


# 模型训练
def train(model, train_loader, epoch):
    model.train()
    train_loss = 0
    for i, data in enumerate(train_loader, 0):
        x, y = data
        x = x.cuda()
        y = y.cuda()
        optimizer.zero_grad()
        y_hat = model(x)
        loss = criterion(y_hat, y)
        loss.backward()
        optimizer.step()
        train_loss += loss
    loss_mean = train_loss / (i+1)
    print('Train Epoch: {}\t Loss: {:.6f}'.format(epoch, loss_mean.item()))


def main():
    # 如果有保存的模型，则加载模型，并在其基础上继续训练
    if os.path.exists(log_dir):
        checkpoint = torch.load(log_dir)
        model.load_state_dict(checkpoint['model'])
        optimizer.load_state_dict(checkpoint['optimizer'])
        start_epoch = checkpoint['epoch']
        print('加载 epoch {} 成功！'.format(start_epoch))
    else:
        start_epoch = 0
        print('无保存模型，将从头开始训练！')

    for epoch in range(start_epoch+1, epochs):
        train(model, train_load, epoch)
        # 保存模型
        state = {'model':model.state_dict(), 'optimizer':optimizer.state_dict(), 'epoch':epoch}
        torch.save(state, log_dir)

if __name__ == '__main__':
    main()