pytorch笔记-实现一个图像分类模型

1.数据引入

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

2.训练集与测试集

我们用到的数据集是FashionMNIST，是一个图像数据集，用它来进行分类任务。
dataloader用来存放相应的训练数据以及对应的标签
dataset将包装一个可迭代的数据集，

在这里插入代码片
# 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(),
)
'''
dataset作为dataloader的参数传入，在数据集上包裹一个可迭代的对象，支持batchsize 加载，混淆，多进程数据加载
'''
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

3.创建模型

从nn.Module继承并创建一个类，用来定义网络结构

# Get cpu or gpu device for training.
device = "cuda" if torch.cuda.is_available() else "cpu"
print(f"Using {device} device")
# Define model
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().to(device)
print(model)

4.模型超参优化

定义损失函数和用的优化器

loss_fn = nn.CrossEntropyLoss() 
optimizer =torch.optim.SGD(model.parameters(), lr=1e-3)

训练与反向传播代码

def train(dataloader, model, loss_fn, optimizer):
    size = len(dataloader.dataset)
    model.train()
    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)
        # 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}]")

在训练过程中模型的测试代码

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")

训练过程会持续几个epoch，每经历一个epoch模型学的参数会进行更好的预测。随着训练的进行，模型良好的趋势是模型的accuracy会不断的提高，loss会逐步的下降。

epochs = 5
for t in range(epochs):
    print(f"Epoch {t+1}\n-------------------------------")
    train(train_dataloader, model, loss_fn, optimizer)
    test(test_dataloader, model, loss_fn)
print("Done!")

5.模型保存

保存模型的一个常见方法是序列化内部状态字典（包含模型参数）。

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

6.模型加载与预测

加载模型的过程包括重新创建模型结构并将状态字典加载到其中。

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

加载完模型后可用来进行预测

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():
    pred = model(x)
    predicted, actual = classes[pred[0].argmax(0)], classes[y]
    print(f'Predicted: "{predicted}", Actual: "{actual}"')

7.参考资料

https://pytorch.org/tutorials/beginner/basics/quickstart_tutorial.html.