最简单的网络

引入包

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

导入数据

# Download training data from open datasets.
training_data = datasets.FashionMNIST(
    root="data",
    train=True,
    download=True,
    transform=ToTensor(),
)

# Download test data from open datasets.
test_data = datasets.FashionMNIST(
    root="data",
    train=False,
    download=True,
    transform=ToTensor(),
)

数据dataset 处理成 dataloader

batch_size = 64

# Create data loaders.
train_dataloader = DataLoader(training_data, batch_size=batch_size)
test_dataloader = DataLoader(test_data, batch_size=batch_size)

for X, y in test_dataloader:
    print(f"Shape of X [N, C, H, W]: {X.shape}")
    print(f"Shape of y: {y.shape} {y.dtype}")
    break

构造模型

# Get cpu, gpu or mps device for training.
device = (
    "cuda"
    if torch.cuda.is_available()
    else "mps"
    if torch.backends.mps.is_available()
    else "cpu"
)
print(f"Using {device} device")

# Define model
class NeuralNetwork(nn.Module):
    def __init__(self):
        # 定义网络
        super().__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):
        # 定义前向计算方式
        x = self.flatten(x)
        logits = self.linear_relu_stack(x)
        return logits

model = NeuralNetwork().to(device)
print(model)

模型参数优化

loss_fn = nn.CrossEntropyLoss() # 损失函数
optimizer = torch.optim.SGD(model.parameters(), lr=1e-3) # 优化器

训练模型

def train(dataloader, model, loss_fn, optimizer):
    size = len(dataloader.dataset)
    model.train() # 模型开始训练
    for batch, (X, y) in enumerate(dataloader):
        X, y = X.to(device), y.to(device)

        # Compute prediction error
        pred = model(X)
        loss = loss_fn(pred, y)  # 计算损失

        # Backpropagation
        loss.backward()  # 反向传播
        optimizer.step() # 梯度更新
        optimizer.zero_grad() # 梯度重置

        if batch % 100 == 0:
            loss, current = loss.item(), (batch + 1) * len(X)
            print(f"loss: {loss:>7f}  [{current:>5d}/{size:>5d}]")

测试模型

def test(dataloader, model, loss_fn):
    size = len(dataloader.dataset)
    num_batches = len(dataloader)
    model.eval()
    test_loss, correct = 0, 0
    with torch.no_grad():
        for X, y in dataloader:
            X, y = X.to(device), y.to(device)
            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")

保存和加载模型

保存模型

torch.save(model.state_dict(), "model.pth")
print("Saved PyTorch Model State to model.pth")

加载模型

model = NeuralNetwork().to(device)
model.load_state_dict(torch.load("model.pth"))

预测结果

classes = [
    "T-shirt/top",
    "Trouser",
    "Pullover",
    "Dress",
    "Coat",
    "Sandal",
    "Shirt",
    "Sneaker",
    "Bag",
    "Ankle boot",
]

model.eval()
x, y = test_data[0][0], test_data[0][1]
with torch.no_grad():
    x = x.to(device)
    pred = model(x)
    predicted, actual = classes[pred[0].argmax(0)], classes[y]
    print(f'Predicted: "{predicted}", Actual: "{actual}"')

更简单的代码示例

import torch
import torch.nn as nn

class SimpleModel(nn.Module):
    def __init__(self):
        super(SimpleModel, self).__init__()
        self.dropout = nn.Dropout(p=0.5)
        self.fc = nn.Linear(10, 2)

    def forward(self, x):
        x = self.dropout(x)
        x = self.fc(x)
        return x

# 创建模型实例
model = SimpleModel()

# 切换到训练模式
model.train()

# 输入一些示例数据
input_data = torch.randn(5, 10)
output_data = model(input_data)
print("Training mode output:", output_data)

# 切换到评估模式
model.eval()

# 输入一些示例数据
output_data = model(input_data)
print("Evaluation mode output:", output_data)

# 模型实例
model = SimpleModel()
optimizer = torch.optim.Adam(model.parameters(), lr=0.001)
criterion = nn.CrossEntropyLoss()

# 训练模型
for epoch in range(epochs):
    model.train()  # 切换到训练模式
    for inputs, targets in train_loader:
        optimizer.zero_grad()
        outputs = model(inputs)
        loss = criterion(outputs, targets)
        loss.backward()
        optimizer.step()

    # 评估模型
    model.eval()  # 切换到评估模式
    with torch.no_grad():
        for inputs, targets in val_loader:
            outputs = model(inputs)
            val_loss = criterion(outputs, targets)
            # 计算评价指标