{"library":"jraph","type":"library","category":null,"description":"Jraph (pronounced \"giraffe\") is a lightweight library for building Graph Neural Networks (GNNs) in JAX. It provides a fundamental data structure for graphs (`GraphsTuple`), a set of utilities for working with graphs (e.g., batching, padding, message passing), and a 'zoo' of forkable GNN models. Leveraging JAX's automatic differentiation and XLA compilation, Jraph aims for high performance and flexibility in GNN research. It is currently in a pre-release development state (v0.0.6.dev0) with frequent updates.","language":"python","status":"active","version":"0.0.6.dev0","tags":["Graph Neural Networks","GNN","JAX","Deep Learning","Graphs"],"last_verified":"Mon May 25","install":[{"cmd":"pip install jraph","imports":["from jraph import GraphsTuple","from jraph.models import GraphNetwork","from jraph import batch"]},{"cmd":"pip install git+git://github.com/deepmind/jraph.git","imports":[]}],"homepage":null,"github":"https://github.com/deepmind/jraph","docs":null,"changelog":null,"pypi":"https://pypi.org/project/jraph/","npm":null,"openapi_spec":null,"status_page":null,"smithery":null,"compatibility":{"summary":{"python_range":"3.10–3.9","success_rate":25,"avg_install_s":12,"avg_import_s":2,"wheel_type":"wheel"},"url":"https://checklist.day/v1/registry/jraph/compatibility"}}