Pytorch学习笔记5——优化和加载保存模型

Pytorch Learning Notes

Reference：
Pytorch官方文档——SAVE AND LOAD THE MODEL
Pytorch官方文档——OPTIMIZING MODEL PARAMETERS

以上是Pytorch官方的文档，本文主要对其进行翻译整理，并加入一些自己的理解，仅作日后复习查阅所用。

1.Optimization

搭建完模型load完数据后，便需要对模型的参数进行优化，即训练这一过程。

1.1 先前的代码

import torch
from torch import nn
from torch.utils.data import DataLoader
from torchvision import datasets
from torchvision.transforms import ToTensor, Lambda

training_data = datasets.FashionMNIST(
    root="data",
    train=True,
    download=True,
    transform=ToTensor()
)

test_data = datasets.FashionMNIST(
    root="data",
    train=False,
    download=True,
    transform=ToTensor()
)

train_dataloader = DataLoader(training_data, batch_size=64)
test_dataloader = DataLoader(test_data, batch_size=64)

class NeuralNetwork(nn.Module):
    def __init__(self):
        super(NeuralNetwork, self).__init__()
        self.flatten = nn.Flatten()
        self.linear_relu_stack = nn.Sequential(
            nn.Linear(28*28, 512),
            nn.ReLU(),
            nn.Linear(512, 512),
            nn.ReLU(),
            nn.Linear(512, 10),
        )

    def forward(self, x):
        x = self.flatten(x)
        logits = self.linear_relu_stack(x)
        return logits

model = NeuralNetwork()

1.2 超参数

定义如下训练时的超参数：Epoch数（迭代循环次数）、Batch Size、Learning Rate学习率

1.3 Epoch

一个Epoch包含两个步骤：1、训练过程，训练修改网络参数使结果向预期结果收敛；2、验证(Validation)过程，输入测试数据，检验网络的performance。

1.4 损失函数

损失函数衡量网络的表现状况（通过比较预期输出与实际网络输出）。

1.5 Optimizer

Optimization是每个epoch中修改模型参数从而减少损失函数error的过程。训练过程中的优化主要分为三个步骤：1、运行optimizer.zero_grad()函数将模型参数的梯度置零；2、运行 loss.backwards()函数反向传播loss；3、有梯度后，运行optimizer.step()对参数进行修改。

1.6 Full Implementation

def train_loop(dataloader, model, loss_fn, optimizer):
    size = len(dataloader.dataset)
    for batch, (X, y) in enumerate(dataloader):
        # Compute prediction and loss
        pred = model(X)
        loss = loss_fn(pred, y)

        # Backpropagation
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

        if batch % 100 == 0:
            loss, current = loss.item(), batch * len(X)
            print(f"loss: {loss:>7f}  [{current:>5d}/{size:>5d}]")


def test_loop(dataloader, model, loss_fn):
    size = len(dataloader.dataset)
    num_batches = len(dataloader)
    test_loss, correct = 0, 0

    with torch.no_grad():
        for X, y in dataloader:
            pred = model(X)
            test_loss += loss_fn(pred, y).item()
            correct += (pred.argmax(1) == y).type(torch.float).sum().item()

    test_loss /= num_batches
    correct /= size
    print(f"Test Error: \n Accuracy: {(100*correct):>0.1f}%, Avg loss: {test_loss:>8f} \n")
    
loss_fn = nn.CrossEntropyLoss()
optimizer = torch.optim.SGD(model.parameters(), lr=learning_rate)

epochs = 10
for t in range(epochs):
    print(f"Epoch {t+1}\n-------------------------------")
    train_loop(train_dataloader, model, loss_fn, optimizer)
    test_loop(test_dataloader, model, loss_fn)
print("Done!")

2.SAVE AND LOAD THE MODEL

import torch
import torchvision.models as models

#加载训练好的模型，并将参数存入内部字典
model = models.vgg16(pretrained=True)
torch.save(model.state_dict(), 'model_weights.pth')

#加载模型，并load模型参数
model = models.vgg16() # we do not specify pretrained=True, i.e. do not load default weights
model.load_state_dict(torch.load('model_weights.pth'))
model.eval()

#若想存参数和模型结构
torch.save(model, 'model.pth')
#加载模型和参数
model = torch.load('model.pth')