thinc crystal_ball A refreshing functional take on deep learning, compatible with your favorite libraries ยถ
See also
Annonces ยถ
Features ยถ
๐ Type checking ยถ
Develop faster and catch bugs sooner with sophisticated type checking.
Trying to pass a 1-dimensional array into a model that expects 2 dimensions ? Thatโs a type error. Your editor can pick it up as the code leaves your fingers.
๐ Awesome config ยถ
See also
Configuration is a major pain for ML.
Thinc lets you describe trees of objects, with references to your own functions, so you can stop passing around blobs of settings. Itโs simple, clean, and it works for both research and production.
๐ฎ Use any framework ยถ
Switch between PyTorch, TensorFlow and MXNet models without changing your application, or even create mutant hybrids using zero-copy array interchange.