Pytorch入门

最新推荐文章于 2025-05-13 22:42:25 发布

m0_54441309

最新推荐文章于 2025-05-13 22:42:25 发布

阅读量103

点赞数

文章标签： pytorch 深度学习 python

原文链接：https://pytorch.org/tutorials/recipes/recipes/saving_and_loading_models_for_inference.html

版权

这篇博客详细介绍了如何在PyTorch中定义、初始化神经网络，使用SGD优化器，并展示了如何保存和加载模型的state_dict以及整个模型。还讲解了如何保存常规检查点，包括模型状态、优化器状态和训练损失，并在之后如何加载这些检查点继续训练。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

翻译自Pytorch官方英文文档

1.定义并初始化神经网络

import torch
import torch.nn as nn
import torch.optim as optim
import torch.nn.functional as F

class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(3, 6, 5)
        self.pool = nn.MaxPool2d(2, 2)
        self.conv2 = nn.Conv2d(6, 16, 5)
        self.fc1 = nn.Linear(16 * 5 * 5, 120)
        self.fc2 = nn.Linear(120, 84)
        self.fc3 = nn.Linear(84, 10)

    def forward(self, x):
        x = self.pool(F.relu(self.conv1(x)))
        x = self.pool(F.relu(self.conv2(x)))
        x = x.view(-1, 16 * 5 * 5)
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        x = self.fc3(x)
        return x

net = Net()
print(net)

2.初始化优化器

optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)

3.通过state_dict保存并加载模型

# Specify a path
PATH = "state_dict_model.pt"

# Save
torch.save(net.state_dict(), PATH)

# Load
model = Net()
model.load_state_dict(torch.load(PATH))
model.eval()

4.保存并加载整个模型

# Specify a path
PATH = "entire_model.pt"

# Save
torch.save(net, PATH)

# Load
model = torch.load(PATH)
model.eval()

5.保存常规检查点
收集所有相关信息并建立字典。

# Additional information
EPOCH = 5
PATH = "model.pt"
LOSS = 0.4

torch.save({
            'epoch': EPOCH,
            'model_state_dict': net.state_dict(),
            'optimizer_state_dict': optimizer.state_dict(),
            'loss': LOSS,
            }, PATH)

6.加载常规检查点
记住首先初始化模型和优化器，然后在本地加载字典。

model = Net()
optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)

checkpoint = torch.load(PATH)
model.load_state_dict(checkpoint['model_state_dict'])
optimizer.load_state_dict(checkpoint['optimizer_state_dict'])
epoch = checkpoint['epoch']
loss = checkpoint['loss']

model.eval()
# - or -
model.train()