PyTorch documentation

PyTorch is an optimized tensor library for deep learning using GPUs and CPUs.

Notes

• Autograd mechanics
• Broadcasting semantics
• CUDA semantics
• Extending PyTorch
• Frequently Asked Questions
• Multiprocessing best practices
• Serialization semantics
• Windows FAQ

Package Reference

• torch
• torch.Tensor
• Tensor Attributes
• torch.sparse
• torch.cuda
• torch.Storage
• torch.nn
• torch.nn.functional
• torch.nn.init
• torch.optim
• torch.autograd
• torch.distributions
• torch.multiprocessing
• torch.distributed
• torch.utils.bottleneck
• torch.utils.checkpoint
• torch.utils.cpp_extension
• torch.utils.data
• torch.utils.ffi
• torch.utils.model_zoo
• torch.onnx
• torch.legacy

torchvision Reference

• torchvision
  • torchvision.datasets
  • torchvision.models
  • torchvision.transforms
  • torchvision.utils

Indices and tables

• Index
• Module Index