PyTorch深度学习环境搭建

PyTorch深度学习环境搭建

PyTorch是一个开源的深度学习框架，提供了灵活的神经网络构建和训练能力。

环境准备

# 创建虚拟环境
conda create -n pytorch python=3.9
conda activate pytorch

# 安装PyTorch (CPU版本)
conda install pytorch torchvision torchaudio cpuonly -c pytorch

# 安装PyTorch (GPU版本)
conda install pytorch torchvision torchaudio pytorch-cuda=11.8 -c pytorch -c nvidia

验证安装

import torch
import torchvision

print(f"PyTorch版本: {torch.__version__}")
print(f"CUDA可用: {torch.cuda.is_available()}")
if torch.cuda.is_available():
    print(f"GPU数量: {torch.cuda.device_count()}")
    print(f"当前GPU: {torch.cuda.get_device_name(0)}")

简单神经网络示例

import torch
import torch.nn as nn
import torch.optim as optim

# 定义模型
class SimpleNet(nn.Module):
    def __init__(self):
        super(SimpleNet, self).__init__()
        self.fc1 = nn.Linear(784, 128)
        self.fc2 = nn.Linear(128, 64)
        self.fc3 = nn.Linear(64, 10)
        self.relu = nn.ReLU()
        
    def forward(self, x):
        x = self.relu(self.fc1(x))
        x = self.relu(self.fc2(x))
        x = self.fc3(x)
        return x

# 创建模型实例
model = SimpleNet()
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters(), lr=0.001)

数据加载

from torch.utils.data import DataLoader
from torchvision import datasets, transforms

# 数据预处理
transform = transforms.Compose([
    transforms.ToTensor(),
    transforms.Normalize((0.5,), (0.5,))
])

# 加载数据集
train_dataset = datasets.MNIST(root="./data", train=True, download=True, transform=transform)
train_loader = DataLoader(train_dataset, batch_size=64, shuffle=True)

模型训练

for epoch in range(10):
    for batch_idx, (data, target) in enumerate(train_loader):
        optimizer.zero_grad()
        output = model(data.view(-1, 784))
        loss = criterion(output, target)
        loss.backward()
        optimizer.step()
        
        if batch_idx % 100 == 0:
            print(f"Epoch: {epoch}, Batch: {batch_idx}, Loss: {loss.item():.4f}")