1. Quickstart

本文展示了如何使用pytorch，来实现神经网络训练。得益于训练结构的通用性，大部分卷积网络只需要在此基础上进行简单的修改就可以。

1.1 训练数据

导入pytorch的包。

python

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

pytorch，提供两个用于数据处理的包：torch.utils.data.DataLoader 和 torch.utils.data.Dataset. Dataset 存储样本及其相应的标签，DataLoader在Dataset周围包裹了一个迭代对象。

PyTorch提供特定于领域的库，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模块包含许多现实世界视觉数据的数据集对象，例如CIFAR、COCO（此处完整列表）。在本教程中，我们使用FashionMNIST数据集。每个TorchVision数据集都包括两个参数：transform和Target_transform，用于分别修改样本和标签。

python

# 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(),
)

out

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

  0%|          | 0.00/26.4M [00:00<?, ?B/s]
  0%|          | 65.5k/26.4M [00:00<01:11, 368kB/s]
  1%|          | 229k/26.4M [00:00<00:37, 697kB/s]
  4%|3         | 950k/26.4M [00:00<00:11, 2.23MB/s]
 15%|#4        | 3.83M/26.4M [00:00<00:02, 7.73MB/s]
 37%|###7      | 9.83M/26.4M [00:00<00:00, 17.0MB/s]
 57%|#####7    | 15.1M/26.4M [00:00<00:00, 25.0MB/s]
 72%|#######2  | 19.1M/26.4M [00:01<00:00, 24.4MB/s]
 93%|#########2| 24.4M/26.4M [00:01<00:00, 30.9MB/s]
100%|##########| 26.4M/26.4M [00:01<00:00, 19.6MB/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

  0%|          | 0.00/29.5k [00:00<?, ?B/s]
100%|##########| 29.5k/29.5k [00:00<00:00, 329kB/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

  0%|          | 0.00/4.42M [00:00<?, ?B/s]
  1%|1         | 65.5k/4.42M [00:00<00:11, 372kB/s]
  5%|5         | 229k/4.42M [00:00<00:06, 698kB/s]
 21%|##        | 918k/4.42M [00:00<00:01, 2.62MB/s]
 44%|####3     | 1.93M/4.42M [00:00<00:00, 4.21MB/s]
100%|##########| 4.42M/4.42M [00:00<00:00, 6.22MB/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

  0%|          | 0.00/5.15k [00:00<?, ?B/s]
100%|##########| 5.15k/5.15k [00:00<00:00, 31.3MB/s]
Extracting data/FashionMNIST/raw/t10k-labels-idx1-ubyte.gz to data/FashionMNIST/raw

我们将Dataset作为参数传递给DataLoader 。这在我们的数据集上包装了一个可迭代对象，并支持自动批处理、采样、打乱数据（shuffling）和多进程数据加载。这里我们定义批量大小为 64，即数据加载器迭代中的每个元素将返回一批 64 个特征和标签。

python


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

OUT

python

Shape of X [N, C, H, W]: torch.Size([64, 1, 28, 28])
Shape of y: torch.Size([64]) torch.int64

Read more about loading data in PyTorch.

1.2 创建模型

为了在 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__函数中定义网络层，并forward函数中指定数据如何通过网络。为了加速神经网络中的操作，我们将其转移到 GPU 或 MPS（如果可用）。

python

# 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)

OUT

python

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)
  )
)

阅读有关在 PyTorch 中构建神经网络的更多信息。

1.3 优化模型参数

为了训练模型，我们需要一个损失函数和一个优化器。

python

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（批量输入）进行预测，并反向传播预测误差以调整模型的参数。

python

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

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")

训练过程需要经过多次迭代（ epochs ）。在每个时期，模型都会学习参数以做出更好的预测。我们打印每个时期模型的准确性和损失；我们希望看到每个 epoch 的准确率都会提高，损失也会减少。

python

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!")

OUT

python

Epoch 1
-------------------------------
loss: 2.303494  [   64/60000]
loss: 2.294637  [ 6464/60000]
loss: 2.277102  [12864/60000]
loss: 2.269977  [19264/60000]
loss: 2.254235  [25664/60000]
loss: 2.237146  [32064/60000]
loss: 2.231055  [38464/60000]
loss: 2.205037  [44864/60000]
loss: 2.203240  [51264/60000]
loss: 2.170889  [57664/60000]
Test Error:
 Accuracy: 53.9%, Avg loss: 2.168588

Epoch 2
-------------------------------
loss: 2.177787  [   64/60000]
loss: 2.168083  [ 6464/60000]
loss: 2.114910  [12864/60000]
loss: 2.130412  [19264/60000]
loss: 2.087473  [25664/60000]
loss: 2.039670  [32064/60000]
loss: 2.054274  [38464/60000]
loss: 1.985457  [44864/60000]
loss: 1.996023  [51264/60000]
loss: 1.917241  [57664/60000]
Test Error:
 Accuracy: 60.2%, Avg loss: 1.920374

Epoch 3
-------------------------------
loss: 1.951705  [   64/60000]
loss: 1.919516  [ 6464/60000]
loss: 1.808730  [12864/60000]
loss: 1.846550  [19264/60000]
loss: 1.740618  [25664/60000]
loss: 1.698733  [32064/60000]
loss: 1.708889  [38464/60000]
loss: 1.614436  [44864/60000]
loss: 1.646475  [51264/60000]
loss: 1.524308  [57664/60000]
Test Error:
 Accuracy: 61.4%, Avg loss: 1.547092

Epoch 4
-------------------------------
loss: 1.612695  [   64/60000]
loss: 1.570870  [ 6464/60000]
loss: 1.424730  [12864/60000]
loss: 1.489542  [19264/60000]
loss: 1.367256  [25664/60000]
loss: 1.373464  [32064/60000]
loss: 1.376744  [38464/60000]
loss: 1.304962  [44864/60000]
loss: 1.347154  [51264/60000]
loss: 1.230661  [57664/60000]
Test Error:
 Accuracy: 62.7%, Avg loss: 1.260891

Epoch 5
-------------------------------
loss: 1.337803  [   64/60000]
loss: 1.313278  [ 6464/60000]
loss: 1.151837  [12864/60000]
loss: 1.252142  [19264/60000]
loss: 1.123048  [25664/60000]
loss: 1.159531  [32064/60000]
loss: 1.175011  [38464/60000]
loss: 1.115554  [44864/60000]
loss: 1.160974  [51264/60000]
loss: 1.062730  [57664/60000]
Test Error:
 Accuracy: 64.6%, Avg loss: 1.087374

Done!

阅读有关训练模型的更多信息。

1.4 保存模型

保存模型的常见方法是序列化内部状态字典（包含模型参数）。

python

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

Saved PyTorch Model State to model.pth

1.5 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

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

该模型现在可用于进行预测。

python

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}"')

Predicted: "Ankle boot", Actual: "Ankle boot"

阅读有关保存和加载模型的更多信息。

参考资料

本文主要翻译自pyorch官方的英文文档 https://pytorch.org/tutorials/beginner/basics/intro.html

1. Quickstart ​

1.1 训练数据 ​

1.2 创建模型 ​

1.3 优化模型参数 ​

1.4 保存模型 ​

1.5 加载模型 ​

参考资料 ​

1. Quickstart

1.1 训练数据

1.2 创建模型

1.3 优化模型参数

1.4 保存模型

1.5 加载模型

参考资料