官網(wǎng)鏈接
Quickstart — PyTorch Tutorials 2.0.1+cu117 documentation
快速開始
本節(jié)將介紹機器學習中常見任務(wù)的API。請參閱每個部分中的鏈接以深入了解。
數(shù)據(jù)處理
PyTorch有兩個處理數(shù)據(jù)源，torch.utils.data.DataLoader 和 torch.utils.data.Dataset 。Dataset存儲樣本及其相應(yīng)的標簽，DataLoader在Dataset之上包裝一個可迭代對象。
import torch
from torch import nn
from torch.utils.data import DataLoader
from torchvision import datasets
from torchvision.transforms import ToTensorPyTorch提供了特定領(lǐng)域的庫，如TorchText, TorchVision和TorchAudio，它們都包含數(shù)據(jù)集。在本教程中，我們將使用TorchVision數(shù)據(jù)集。
torchvision.datasets 模塊包含了真實數(shù)據(jù)的Dataset對象。比如 CIFAR, COCO（完整列表參考Datasets — Torchvision 0.15 documentation）。在本教程中，我們使用FashionMNIST數(shù)據(jù)集。每個TorchVision數(shù)據(jù)集包含兩個參數(shù):transform和target_transform，分別用于修改樣本和標簽。
# 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(),
)我們將Dataset作為DataLoader的入?yún)?，Dataset在數(shù)據(jù)集上包裝了一個可迭代對象，并支持自動批處理、采樣、洗牌和多進程數(shù)據(jù)加載。這里我們定義了一個批處理大小為64，即dataloader可迭代對象中的每個元素將返回一批64個特征和標簽。
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輸出：
Shape of X [N, C, H, W]: torch.Size([64, 1, 28, 28])
Shape of y: torch.Size([64]) torch.int64創(chuàng)建模型
為了在PyTorch中定義一個神經(jīng)網(wǎng)絡(luò)，我們創(chuàng)建了一個繼承了nn.Module的類，我們在__init__函數(shù)中定義網(wǎng)絡(luò)層，并在forward函數(shù)中指定數(shù)據(jù)如何通過網(wǎng)絡(luò)。為了加速神經(jīng)網(wǎng)絡(luò)的操作，我們將其轉(zhuǎn)移到GPU或MPS(如果可用)。
注：
PyTorch MPS (Multi-Process Service)是 PyTorch 中的一種分布式訓練方式。它是基于Apple的MPS(Metal Performance Shaders) 框架開發(fā)的
# 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)輸出
Using mps 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)
)
)注：因為我的設(shè)備是蘋果，所以輸出是mps,跟官網(wǎng)顯示不同
優(yōu)化模型參數(shù)
為了訓練一個模型，我們需要一個損失函數(shù)和一個優(yōu)化器。
loss_fn = nn.CrossEntropyLoss()
optimizer = torch.optim.SGD(model.parameters(), lr=1e-3)在單個訓練循環(huán)中，模型對訓練數(shù)據(jù)集進行預(yù)測(批量提供給它)，并反向傳播預(yù)測誤差以調(diào)整模型的參數(shù)。
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}]")我們還根據(jù)測試數(shù)據(jù)集檢查模型的性能，以確保它正在學習。
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")訓練過程在幾個迭代(epochs)中進行。在每個epochs，模型學習參數(shù)以做出更好的預(yù)測。我們打印出模型在每個epochs的精度和損失;我們希望看到精度隨著時間的推移而提高，損失隨著時間的推移而減少。
輸出
Epoch 1
-------------------------------
loss: 2.304695 [ 64/60000]
loss: 2.293914 [ 6464/60000]
loss: 2.271139 [12864/60000]
loss: 2.267832 [19264/60000]
loss: 2.240983 [25664/60000]
loss: 2.217048 [32064/60000]
loss: 2.230957 [38464/60000]
loss: 2.190546 [44864/60000]
loss: 2.180454 [51264/60000]
loss: 2.167166 [57664/60000]
Test Error:
Accuracy: 43.7%, Avg loss: 2.148366
Epoch 2
-------------------------------
loss: 2.155765 [ 64/60000]
loss: 2.153187 [ 6464/60000]
loss: 2.084353 [12864/60000]
loss: 2.106838 [19264/60000]
loss: 2.051079 [25664/60000]
loss: 1.998855 [32064/60000]
loss: 2.030421 [38464/60000]
loss: 1.942099 [44864/60000]
loss: 1.941234 [51264/60000]
loss: 1.891874 [57664/60000]
Test Error:
Accuracy: 55.8%, Avg loss: 1.873747
Epoch 3
-------------------------------
loss: 1.904033 [ 64/60000]
loss: 1.885520 [ 6464/60000]
loss: 1.749947 [12864/60000]
loss: 1.801118 [19264/60000]
loss: 1.690538 [25664/60000]
loss: 1.652585 [32064/60000]
loss: 1.680197 [38464/60000]
loss: 1.571219 [44864/60000]
loss: 1.597052 [51264/60000]
loss: 1.505626 [57664/60000]
Test Error:
Accuracy: 61.0%, Avg loss: 1.510632
Epoch 4
-------------------------------
loss: 1.579605 [ 64/60000]
loss: 1.553953 [ 6464/60000]
loss: 1.388195 [12864/60000]
loss: 1.468328 [19264/60000]
loss: 1.347958 [25664/60000]
loss: 1.354385 [32064/60000]
loss: 1.368013 [38464/60000]
loss: 1.285745 [44864/60000]
loss: 1.321613 [51264/60000]
loss: 1.226315 [57664/60000]
Test Error:
Accuracy: 63.1%, Avg loss: 1.248957
Epoch 5
-------------------------------
loss: 1.330482 [ 64/60000]
loss: 1.320243 [ 6464/60000]
loss: 1.139326 [12864/60000]
loss: 1.250566 [19264/60000]
loss: 1.124903 [25664/60000]
loss: 1.160373 [32064/60000]
loss: 1.176003 [38464/60000]
loss: 1.108413 [44864/60000]
loss: 1.148409 [51264/60000]
loss: 1.063753 [57664/60000]
Test Error:
Accuracy: 64.3%, Avg loss: 1.086042
Done!保存模型
保存模型的一種常用方法是序列化內(nèi)部狀態(tài)字典(包含模型參數(shù))。
torch.save(model.state_dict(), "model.pth")
print("Saved PyTorch Model State to model.pth")輸出
Saved PyTorch Model State to model.pth加載模型
model = NeuralNetwork().to(device)
model.load_state_dict(torch.load("model.pth"))這個模型現(xiàn)在可以用來做預(yù)測。文章來源：http://www.zghlxwxcb.cn/news/detail-499260.html
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}"')輸出文章來源地址http://www.zghlxwxcb.cn/news/detail-499260.html
Predicted: "Ankle boot", Actual: "Ankle boot"到了這里，關(guān)于PyTorch翻譯官網(wǎng)教程1-QUICKSTART的文章就介紹完了。如果您還想了解更多內(nèi)容，請在右上角搜索TOY模板網(wǎng)以前的文章或繼續(xù)瀏覽下面的相關(guān)文章，希望大家以后多多支持TOY模板網(wǎng)！
