{"library":"torch-geometric","type":"library","category":null,"description":"PyTorch Geometric (PyG) is a library built upon PyTorch to easily write and train Graph Neural Networks (GNNs) for a wide range of applications related to structured data. It consists of various methods for deep learning on graphs and other irregular structures, providing easy-to-use mini-batch loaders, multi-GPU support, `torch.compile` support, a large number of common benchmark datasets, and helpful transforms. It is actively maintained with frequent minor releases delivering new features and bug fixes.","language":"python","status":"active","version":"2.7.0","tags":["graph neural networks","pytorch","deep learning","geometric deep learning","GNN"],"last_verified":"Fri May 22","install":[{"cmd":"pip install torch_geometric","imports":["from torch_geometric.data import Data","from torch_geometric.nn import MessagePassing","from torch_geometric.nn import GCNConv","from torch_geometric.datasets import Planetoid","import torch_geometric.transforms as T"]},{"cmd":"# Ensure PyTorch is installed with appropriate CUDA support, e.g., for CUDA 12.1:\npip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu121\n# Then install PyG's optional C++/CUDA extensions (replace TORCH and CUDA with your versions):\npip install pyg_lib torch_scatter torch_sparse torch_cluster torch_spline_conv -f https://data.pyg.org/whl/torch-${TORCH}+${CUDA}.html","imports":[]}],"homepage":"https://pyg.org","github":"https://github.com/pyg-team/pytorch_geometric","docs":"https://pytorch-geometric.readthedocs.io","changelog":"https://github.com/pyg-team/pytorch_geometric/blob/master/CHANGELOG.md","pypi":"https://pypi.org/project/torch-geometric/","npm":null,"openapi_spec":null,"status_page":null,"smithery":null,"compatibility":{"summary":{"python_range":"3.10–3.9","success_rate":100,"avg_install_s":8.2,"avg_import_s":null,"wheel_type":"wheel"},"url":"https://checklist.day/v1/registry/torch-geometric/compatibility"}}