创建一个网络

建立一个简单的三层的网络。

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()

给出网络参数

learning_rate = 1e-3  #学习率，每次沿梯度方向前进步长
batch_size = 64  #每次跟新梯度的数据数
epochs = 5 #总训练迭代次数

损失函数

常见的顺势函数为：

nn.MSELoss : Mean Square Error
nn.NLLoss : Negative Log Likelihood
nn.CrossEntropyLoss: nnLogSoftmax + nn.NLLLoss

# Initialize the loss function
loss_fn = nn.CrossEntropyLoss()

优化器

optimizer表示网络使用何种方法(这里主要涉及梯度和学习率)更新网络参数的过程，常用的梯度更新方式有：

SGD: 随机梯度下降法（stochatic gradient decent）
ADAM: 考虑动量的梯度方法
RMSProp:

详情可参见官方说明: https://pytorch.org/docs/stable/optim.html
一篇非常好的介绍各种梯度方法的博客: https://ruder.io/optimizing-gradient-descent/index.html#adam

optimizer = torch.optim.SGD(model.parameters(), lr=learning_rate)

在每个优化循环中主要包含如下三步：

optimizer.zero_grad(): 清空梯度累计
loss.backward(): 方向传播，使用loss函数累计梯度（累积和batch有关系）
optimizer.step(): 使用累计的梯度，更新参数

完整的训练过程

定义一个train_loop()函数进行网络训练
定一个test_loop()函数反馈网络预测结果
相关函数定义如下：

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")

一个完整的训练，优化过程：

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!")

训练结果的载入和保存

torch 在网络完成训练后，可以将网络参数以字典（ .state_dict() ）的形式保存为.pth文件。

import torch
import torchvision.models as models

model = models.vgg16(pretrained=True)
torch.save(model.state_dict(), 'model_weights.pth')

同样也可以讲一训练好的网络参数导入：

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()

保存网络模型结构

torch.save(model, 'model.pth')

载入网络模型结构

model = torch.load('model.pth')