14、保存与加载PyTorch训练的模型和超参数

news2024/11/29 2:13:38

文章目录

1. state_dict
2. 模型保存
3. check_point
4. 详细保存
5. Docker
6. 机器学习常用库

1. state_dict

nn.Module 类是所有神经网络构建的基类，即自己构建一个深度神经网络也是需要继承自nn.Module类才行，并且nn.Module中的state_dict包含神经网络中的权重weight ，偏置bias,过程量buffer，举例说明：

#!/usr/bin/env python
# -*- coding:utf-8 -*-
# @FileName  :NN_Embedding.py
# @Time      :2024/11/26 22:50
# @Author    :Jason Zhang
import torch
from torch import nn


class MyModel(nn.Module):
    def __init__(self):
        super(MyModel, self).__init__()
        self.linear1 = nn.Linear(3, 4)
        self.relu = nn.ReLU()
        self.linear2 = nn.Linear(4, 5)
        self.batch_norm = nn.BatchNorm2d(4)

    def forward(self, x):
        x = self.linear1(x)
        x = self.relu(x)
        y = self.linear2(x)
        return y


if __name__ == "__main__":
    my_test = MyModel()
    my_keys = my_test.state_dict().keys()
    print(f"my_keys={my_keys}")

结果：
从结果中看出，跟说明的一样，不仅存的是weight,bias ,还有buffer

y_keys=odict_keys(['linear1.weight', 'linear1.bias', 'linear2.weight', 'linear2.bias', 'batch_norm.weight', 'batch_norm.bias', 'batch_norm.running_mean', 'batch_norm.running_var', 'batch_norm.num_batches_tracked'])

2. 模型保存

保存和加载

#!/usr/bin/env python
# -*- coding:utf-8 -*-
# @FileName  :torch_save.py
# @Time      :2024/11/27 21:33
# @Author    :Jason Zhang
import torch
import torchvision.models as models

if __name__ == "__main__":
    run_code = 0
    model = models.vgg16(weights='IMAGENET1K_V1')
    torch.save(model.state_dict(), 'model_weights.pth')
    model.load_state_dict(torch.load('model_weights.pth', weights_only=True))
    model.eval()
    torch.save(model, 'model.pth')

3. check_point

# Define model
import torch
from torch import nn
from torch import optim
import torch.nn.functional as F


class TheModelClass(nn.Module):
    def __init__(self):
        super(TheModelClass, 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


# Initialize model
model = TheModelClass()

# Initialize optimizer
optimizer = optim.SGD(model.parameters(), lr=0.001, momentum=0.9)

# Print model's state_dict
print("Model's state_dict:")
for param_tensor in model.state_dict():
    print(param_tensor, "\t", model.state_dict()[param_tensor].size())

# Print optimizer's state_dict
print("Optimizer's state_dict:")
for var_name in optimizer.state_dict():
    print(var_name, "\t", optimizer.state_dict()[var_name])

Model's state_dict:
conv1.weight 	 torch.Size([6, 3, 5, 5])
conv1.bias 	 torch.Size([6])
conv2.weight 	 torch.Size([16, 6, 5, 5])
conv2.bias 	 torch.Size([16])
fc1.weight 	 torch.Size([120, 400])
fc1.bias 	 torch.Size([120])
fc2.weight 	 torch.Size([84, 120])
fc2.bias 	 torch.Size([84])
fc3.weight 	 torch.Size([10, 84])
fc3.bias 	 torch.Size([10])
Optimizer's state_dict:
state 	 {}
param_groups 	 [{'lr': 0.001, 'momentum': 0.9, 'dampening': 0, 'weight_decay': 0, 'nesterov': False, 'maximize': False, 'foreach': None, 'differentiable': False, 'params': [0, 1, 2, 3, 4, 5, 6, 7, 8, 9]}]