pytorch模型加载与保存，并在保存的模型基础上进行训练

两种方法：
1.只保存参数(官方推荐，消耗的存储空间较小)，详细讲解此方法。
2.保存整个模型结构

一.只保存参数

1.保存：
方法一：

torch.save(model.state_dict(), path)

model：定义的模型的实例变量，如model = resnet()，path是模型保存的路径，如path = “./model.pth”，path = “./model.pkl”，path = “./model.tar”，一定要加上后缀。
方法二：
如果想保存某一次的训练参数和模型，那么可以使用字典的方式进行保存：

state = {"model": model.state_dict(), "optimizer": optimizer.state_dict(), 'epoch': epoch}
torch,save(state, path)

2.加载
针对方法一的模型加载：

model.load_state_dict(torrch.load(path))

针对第二种方法的模型加载：

checkpoint = torch.load(path)
model.load_state_dict(checkpoint['model'])
optimizer.load_state_dict(checkpoint['optimizer'])
epoch = checkpoint['epoch']

只保存参数的模型保存方法在加载模型的时候，加载的模型必须跟事先定义好的模型一致，否者需要调整网络结构(一般是调整最后的输出结构)，并在该模型的实例对象(假设名为model)上进行加载，即在使用上述加载语句前已经有定义了一个和原模型一样的Net, 并且进行了实例化 model=Net( ) 。
如果每一个epoch或每n个epoch都要保存一次参数，可设置不同的path，如 path=’./model’ + str(epoch) +’.pth’，这样，不同epoch的参数就能保存在不同的文件中，选择保存识别率最大的模型参数也一样，只需在保存模型语句前加个if判断语句即可。

实例：只保存最新参数

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

'''本文件用于举例说明pytorch保存和加载文件的方法'''


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()))

# 模型测试
def test(model, test_loader):
    model.eval()
    test_loss = 0
    correct = 0
    with torch.no_grad():
        for i, data in enumerate(test_loader, 0):
            x, y = data
            x = x.cuda()
            y = y.cuda()
            optimizer.zero_grad()
            y_hat = model(x)
            test_loss += criterion(y_hat, y).item()
            pred = y_hat.max(1, keepdim=True)[1]
            correct += pred.eq(y.view_as(pred)).sum().item()
        test_loss /= (i+1)
        print('Test set: Average loss: {:.4f}, Accuracy: {}/{} ({:.0f}%)\n'.format(
            test_loss, correct, len(test_data), 100. * correct / len(test_data)))


def main():

    # 如果test_flag=True,则加载已保存的模型
    if test_flag:
        # 加载保存的模型直接进行测试机验证，不进行此模块以后的步骤
        checkpoint = torch.load(log_dir)
        model.load_state_dict(checkpoint['model'])
        optimizer.load_state_dict(checkpoint['optimizer'])
        epochs = checkpoint['epoch']
        test(model, test_load)
        return

    for epoch in range(0, epochs):
        train(model, train_load, epoch)
        test(model, test_load)
        # 保存模型
        state = {'model':model.state_dict(), 'optimizer':optimizer.state_dict(), 'epoch':epoch}
        torch.save(state, log_dir)

if __name__ == '__main__':
    main()

3.在加载的模型上进行训练：

def main():

    # 如果test_flag=True,则加载已保存的模型
    if test_flag:
        # 加载保存的模型直接进行测试机验证，不进行此模块以后的步骤
        checkpoint = torch.load(log_dir)
        model.load_state_dict(checkpoint['model'])
        optimizer.load_state_dict(checkpoint['optimizer'])
        start_epoch = checkpoint['epoch']
        test(model, test_load)
        return

    # 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)
        test(model, test_load)
        # 保存模型
        state = {'model':model.state_dict(), 'optimizer':optimizer.state_dict(), 'epoch':epoch}
        torch.save(state, log_dir)

二.保存整个模型

1.保存

torch.save(model, path)

2.加载

model = torch.load(path)

本博文参考链接：[https://www.jianshu.com/p/1cd6333128a1]