Pytorch案例

加载数据

PyTorch有两个处理数据的库:torch.utils.data.DataLoader和torch.utils.data.Dataset。数据集存储样本及其对应的标签，DataLoader在数据集周围包装一个可迭代对象。

import torch
from torch import nn
from torch.utils.data import DataLoader
from torchvision import datasets
from torchvision.transforms import ToTensor, Lambda, Compose
import matplotlib.pyplot as plt

torchvision。数据集模块包含许多真实世界的视觉数据的数据集对象，如CIFAR, COCO(完整列表在这里)。在本教程中，我们使用FashionMNIST数据集。每个TorchVision Dataset包含两个参数transform和target_transform，分别修改样本和标签。

# 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(),
)

我们将 Dataset 作为参数传递给 DataLoader。它包装了一个遍历数据集的迭代器，并支持自动批处理、采样、洗牌和多进程数据加载。这里我们定义了一个64的批量大小，也就是说，dataloader 迭代器中的每个元素都将返回一个包含64个特性和标签的批量。

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("Shape of X [N, C, H, W]: ", X.shape)
    print("Shape of y: ", y.shape, y.dtype)
    break

创建模型

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

优化模型参数

loss_fn = nn.CrossEntropyLoss()                                            ## 定义损失函数---交叉熵
optimizer = torch.optim.SGD(model.parameters(), lr=1e-3)                   ## 定义随机梯度优化器SGD

在一个单独的训练循环中，模型对训练数据集进行预测(分批输入)，并反向传播预测误差以调整模型的参数。

我们还根据测试数据集检查模型的性能，以确保它正在学习。

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")

训练过程是在几个迭代(阶段)中进行的。在每个epoch期间，模型学习参数以做出更好的预测。我们打印模型在每个时期的准确性和损失;我们希望看到精确度的提高和损失的减少。

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!")

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

对testdata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}"')