Pytorch快速入门

文章目录

一、使用数据
二、创建模型
三、优化模型参数
四、保存模型
五、加载模型

一、使用数据

PyTorch 有两个用于处理数据的原语：torch.utils.data.DataLoader 和 torch.utils.data.Dataset。 Dataset 存储样本及其对应的标签，而 DataLoader 将一个可迭代对象包装在 Dataset 周围。

python 复制代码

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

PyTorch 提供了特定领域的库，例如 TorchText、TorchVision 和 TorchAudio，所有这些库都包含数据集。在本教程中，我们将使用 TorchVision 数据集。

torchvision.datasets 模块包含许多真实世界视觉数据的 Dataset 对象，例如 CIFAR、COCO。在本教程中，我们将使用 FashionMNIST 数据集。每个 TorchVision Dataset 都包含两个参数：transform 和 target_transform，分别用于修改样本和标签。

python 复制代码

# 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。这将在我们的数据集周围包装一个可迭代对象，并支持自动批处理、采样、洗牌和多进程数据加载。在这里，我们定义了一个大小为 64 的批，即 dataloader 可迭代对象中的每个元素将返回 64 个特征和标签的批。

python 复制代码

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

bash 复制代码

Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/train-images-idx3-ubyte.gz
Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/train-images-idx3-ubyte.gz to data/FashionMNIST/raw/train-images-idx3-ubyte.gz
100%|██████████| 26421880/26421880 [00:07<00:00, 3364333.78it/s]
Extracting data/FashionMNIST/raw/train-images-idx3-ubyte.gz to data/FashionMNIST/raw

Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/train-labels-idx1-ubyte.gz
Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/train-labels-idx1-ubyte.gz to data/FashionMNIST/raw/train-labels-idx1-ubyte.gz
100%|██████████| 29515/29515 [00:00<00:00, 171842.82it/s]
Extracting data/FashionMNIST/raw/train-labels-idx1-ubyte.gz to data/FashionMNIST/raw

Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/t10k-images-idx3-ubyte.gz
Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/t10k-images-idx3-ubyte.gz to data/FashionMNIST/raw/t10k-images-idx3-ubyte.gz
100%|██████████| 4422102/4422102 [00:08<00:00, 544443.31it/s] 
Extracting data/FashionMNIST/raw/t10k-images-idx3-ubyte.gz to data/FashionMNIST/raw

Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/t10k-labels-idx1-ubyte.gz
Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/t10k-labels-idx1-ubyte.gz to data/FashionMNIST/raw/t10k-labels-idx1-ubyte.gz
100%|██████████| 5148/5148 [00:00<00:00, 12157813.62it/s]
Extracting data/FashionMNIST/raw/t10k-labels-idx1-ubyte.gz to data/FashionMNIST/raw

二、创建模型

要在 PyTorch 中定义神经网络，我们创建一个继承自 nn.Module 的类。我们在 init 函数中定义网络的层，并在 forward 函数中指定数据如何通过网络。为了加速神经网络中的运算，如果可用，我们会将其移至 GPU 或 MPS。

python 复制代码

# 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):
        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):
        x = self.flatten(x)
        logits = self.linear_relu_stack(x)
        return logits

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

bash 复制代码

Shape of X [N, C, H, W]: torch.Size([64, 1, 28, 28])
Shape of y: torch.Size([64]) torch.int64
Using cuda device
NeuralNetwork(
  (flatten): Flatten(start_dim=1, end_dim=-1)
  (linear_relu_stack): Sequential(
    (0): Linear(in_features=784, out_features=512, bias=True)
    (1): ReLU()
    (2): Linear(in_features=512, out_features=512, bias=True)
    (3): ReLU()
    (4): Linear(in_features=512, out_features=10, bias=True)
  )
)

三、优化模型参数

要训练模型，我们需要一个损失函数和一个优化器。

python 复制代码

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

在单个训练循环中，模型对训练数据集（分批馈送）进行预测，并将预测误差反向传播以调整模型的参数。

python 复制代码

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

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

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。

python 复制代码

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")

训练过程经过多次迭代（"时期"）。在每个时期，模型都会学习参数以做出更好的预测。我们在每个时期打印模型的准确性和损失；我们希望看到准确性随着每个时期的增加而增加，而损失减少。

python 复制代码

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!")

四、保存模型

保存模型的常用方法是序列化内部状态字典（包含模型参数）。

python 复制代码

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

五、加载模型

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。

python 复制代码

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

该模型现在可用于进行预测。

python 复制代码

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}"')