> ## Documentation Index > Fetch the complete documentation index at: https://base.bangwu.me/llms.txt > Use this file to discover all available pages before exploring further. # PyTorch > PyTorch deep learning framework guide covering CPU and GPU installation, tensor creation and operations, automatic differentiation, and neural network basics. # PyTorch PyTorch is an open-source deep learning framework developed by Facebook AI Research and widely used in both academic research and industry. ## Installation ### Automatic installation Choose the right command from the official website: [https://pytorch.org/get-started/locally/](https://pytorch.org/get-started/locally/) ```bash theme={"theme":{"light":"github-light","dark":"github-dark"}} # CPU 版本 pip install torch torchvision torchaudio # GPU 版本 (CUDA 12.4) pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu124 ``` ### Manual GPU installation Download page: [https://download.pytorch.org/whl/torch/](https://download.pytorch.org/whl/torch/) You need to download three packages, making sure the Python and CUDA versions match: * `torch-2.4.1+cu124-cp312-cp312-win_amd64.whl` * `torchvision-0.19.1+cu124-cp312-cp312-win_amd64.whl` * `torchaudio-2.4.1+cu124-cp312-cp312-win_amd64.whl` ```bash theme={"theme":{"light":"github-light","dark":"github-dark"}} pip install torch-2.4.1+cu124-cp312-cp312-win_amd64.whl pip install torchvision-0.19.1+cu124-cp312-cp312-win_amd64.whl pip install torchaudio-2.4.1+cu124-cp312-cp312-win_amd64.whl ``` ### Verify the installation ```python theme={"theme":{"light":"github-light","dark":"github-dark"}} import torch print(torch.__version__) print(torch.cuda.is_available()) # True 表示 GPU 可用 print(torch.cuda.get_device_name(0)) # 显示 GPU Name ``` ## Basic concepts ### Tensors ```python theme={"theme":{"light":"github-light","dark":"github-dark"}} import torch # 创建张量 x = torch.tensor([1, 2, 3]) y = torch.zeros(2, 3) z = torch.randn(2, 3) # 张量运算 a = torch.tensor([1.0, 2.0]) b = torch.tensor([3.0, 4.0]) c = a + b d = torch.matmul(a, b) # 矩阵乘法 # GPU 加速 if torch.cuda.is_available(): x = x.cuda() # 转移到 GPU # 或者 x = x.to('cuda') ``` ### Automatic differentiation ```python theme={"theme":{"light":"github-light","dark":"github-dark"}} # 需要梯度's 张量 x = torch.tensor([1.0, 2.0], requires_grad=True) y = x ** 2 z = y.sum() # 反向传播 z.backward() print(x.grad) # 梯度: [2.0, 4.0] ``` ## Building neural networks ### Simple model ```python theme={"theme":{"light":"github-light","dark":"github-dark"}} import torch.nn as nn class SimpleNet(nn.Module): def __init__(self): super(SimpleNet, self).__init__() self.fc1 = nn.Linear(784, 128) self.fc2 = nn.Linear(128, 10) self.relu = nn.ReLU() def forward(self, x): x = self.fc1(x) x = self.relu(x) x = self.fc2(x) return x model = SimpleNet() ``` ### Convolutional neural network ```python theme={"theme":{"light":"github-light","dark":"github-dark"}} class CNN(nn.Module): def __init__(self): super(CNN, self).__init__() self.conv1 = nn.Conv2d(1, 32, 3, 1) self.conv2 = nn.Conv2d(32, 64, 3, 1) self.fc1 = nn.Linear(9216, 128) self.fc2 = nn.Linear(128, 10) self.relu = nn.ReLU() self.maxpool = nn.MaxPool2d(2) def forward(self, x): x = self.conv1(x) x = self.relu(x) x = self.maxpool(x) x = self.conv2(x) x = self.relu(x) x = self.maxpool(x) x = x.view(x.size(0), -1) x = self.fc1(x) x = self.relu(x) x = self.fc2(x) return x ``` ## Training a model ```python theme={"theme":{"light":"github-light","dark":"github-dark"}} import torch.optim as optim # 准备数据 train_loader = torch.utils.data.DataLoader(dataset, batch_size=64) # 定义模型、损失函数、优化器 model = SimpleNet() criterion = nn.CrossEntropyLoss() optimizer = optim.Adam(model.parameters(), lr=0.001) # 训练循环 for epoch in range(10): for batch_idx, (data, target) in enumerate(train_loader): # 前向传播 output = model(data) loss = criterion(output, target) # 反向传播 optimizer.zero_grad() loss.backward() optimizer.step() if batch_idx % 100 == 0: print(f'Epoch: {epoch}, Loss: {loss.item()}') ``` ## Data loading ### `Dataset` and `DataLoader` ```python theme={"theme":{"light":"github-light","dark":"github-dark"}} from torch.utils.data import Dataset, DataLoader class CustomDataset(Dataset): def __init__(self, data, labels): self.data = data self.labels = labels def __len__(self): return len(self.data) def __getitem__(self, idx): return self.data[idx], self.labels[idx] dataset = CustomDataset(data, labels) dataloader = DataLoader(dataset, batch_size=32, shuffle=True) ``` ### Image augmentation ```python theme={"theme":{"light":"github-light","dark":"github-dark"}} from torchvision import transforms transform = transforms.Compose([ transforms.Resize(256), transforms.CenterCrop(224), transforms.ToTensor(), transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]) ]) ``` ## Saving and loading models ```python theme={"theme":{"light":"github-light","dark":"github-dark"}} # 保存模型 torch.save(model.state_dict(), 'model.pth') # 加载模型 model = SimpleNet() model.load_state_dict(torch.load('model.pth')) model.eval() # 保存完整模型 torch.save(model, 'model_complete.pth') model = torch.load('model_complete.pth') ``` ## Jupyter Notebook setup Create a dedicated PyTorch kernel: ```bash theme={"theme":{"light":"github-light","dark":"github-dark"}} # 创建虚拟环境 python -m venv pytorch_env # 激活环境 source pytorch_env/bin/activate # Linux/Mac pytorch_env\Scripts\activate # Windows # 安装 PyTorch 和 Jupyter pip install torch torchvision jupyter ipykernel # 创建内核 python -m ipykernel install --user --name=pytorch --display-name "Python (PyTorch)" ``` Reference: [https://blog.csdn.net/ccaoshangfei/article/details/126521809](https://blog.csdn.net/ccaoshangfei/article/details/126521809) ## Useful tips ### Set the random seed ```python theme={"theme":{"light":"github-light","dark":"github-dark"}} torch.manual_seed(42) if torch.cuda.is_available(): torch.cuda.manual_seed(42) ``` ### Show model structure ```python theme={"theme":{"light":"github-light","dark":"github-dark"}} from torchsummary import summary summary(model, input_size=(1, 28, 28)) ``` ### Freeze part of the model ```python theme={"theme":{"light":"github-light","dark":"github-dark"}} # 冻结前两层 for param in model.parameters(): param.requires_grad = False for param in model.fc2.parameters(): param.requires_grad = True ``` ## Learning resources * Official docs: [https://pytorch.org/docs/](https://pytorch.org/docs/) * Official tutorials: [https://pytorch.org/tutorials/](https://pytorch.org/tutorials/) * Chinese docs: [https://pytorch-cn.readthedocs.io/](https://pytorch-cn.readthedocs.io/) * GitHub: [https://github.com/pytorch/pytorch](https://github.com/pytorch/pytorch)