【PyTorch Tutorial学习笔记】PyTorch代码模板（自用）（一）

QUICKSTART

首先展示一个完整的pytorch代码：

1. load data
2. create the model
3. train the model
4. save & load the model

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

### Working with data ###
### step 1: get datasets.
### step 2: get dataloaders. Pass the 'Dataset' as an argument to 'DataLoader'. This supports automatic batching, sampling, shuffling and multiprocess data loading.

# Download training data from open datasets.
training_data = datasets.FashionMNIST(root="data", train=True, download=True, transform=ToTensor())
test_data = datasets.FashionMNIST(root="data", train=False, download=True, transform=ToTensor()）

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

### Creating Models ###
### step 1: create a class that inherits from nn.Module
### step 2: define the layers in '__init__' function
### step 3: define specify the data flow in 'forward' function

# 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),
            nn.ReLU()
        )

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

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

### Optimizing the Model Parameters ###
### step 1: define loss function
### step 2: define optimizer

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

### Traing the Model ###
### step 1: define training process
### -- sub step 1: get data size, and for each data do the following:
### -- sub step 2: go through the model and compute prediction error
### -- sub step 3: do backpropagation
### step 2: define testing process

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() # 重置所有模型参数为0以防止重复计算
        loss.backward() # 反向传播
        optimizer.step() # 利用反向传播中得到的梯度更新参数一步

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

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")

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!")

### Saving the Model ###
### A common way to save a model is to serialize the internal state dictionary (containing the model parameters).

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

### Loading the Model ###
### step 1: re-create the model structure
### step 2: load the state dictionary into the odel
model = NeuralNetwork()
model.load_state_dict(torch.load("model.pth"))

# This model can now be used to make predictions.
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}"')