PyTorch | QuickStart

参考：
https://pytorch.org/tutorials/beginner/basics/intro.html

1. Quickstart

本节给出一个快速入门的例子，具体类别的变量还是要看对应章节的介绍。

1.1 Data

torch.utils.data.Dataset

• Dataset stores the samples and their corresponding labels.
• 所有数据集都要继承的类。

torch.utils.data.DataLoader

• DataLoader wraps an iterable around the Dataset.

• 从Dataset变为Dataloader
  train_dataloader = DataLoader(training_Dataset, batch_size=batch_size)

• DataLoader类似iterator，可以用for循环遍历其中的元素

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

备注：

1. PyTorch offers domain-specific libraries such as TorchText, TorchVision, and TorchAudio, all of which include datasets.如TorchVision预置的数据集

1.2 查询训练用的是CPU还是GPU

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

1.3 创建模型

# 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),
            nn.ReLU()
        )

    def forward(self, x):
        x = self.flatten(x)
        logits = self.linear_relu_stack(x)
        return logits

# 如果能用Cuda就用Cuda。
device = "cuda" if torch.cuda.is_available() else "cpu"
model = NeuralNetwork().to(device)
print(model)

1.4 Optimizing the Model Parameters （优化器设置）

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

然后就可以训练了

1.5 Train & Test

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

def test(dataloader, model):
    size = len(dataloader.dataset)
    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 /= size
    correct /= size
    print(f"Test Error: \n Accuracy: {(100*correct):>0.1f}%, Avg loss: {test_loss:>8f} \n")

1.6 主程序

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

1.7 保存和读取模型

Save

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

Load

import torch
from torch import nn
from torch.utils.data import DataLoader

# 使用视觉库的例子
from torchvision import datasets
from torchvision.transforms import ToTensor, Lambda, Compose
import matplotlib.pyplot as plt


# 1.1 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(),
)

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),
            nn.ReLU()
        )

    def forward(self, x):
        x = self.flatten(x)
        logits = self.linear_relu_stack(x)
        return logits

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

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}"')

2. Tensors

• Tensors are similar to NumPy’s ndarrays, except that tensors can run on GPUs or other hardware accelerators.
• 实际上，Tensors和NumPy数组通常可以共享相同的基础内存，从而无需复制数据。
• Tensors也针对AutoGrad进行了优化。

2.1 初始化一个Tensor

Directly from data (list)
The data type is automatically inferred.

data = [[1, 2