Use any framework
Switch between PyTorch, TensorFlow and MXNet models without changing your application, or even create mutant hybrids using zero-copy array interchange.
Develop faster and catch bugs sooner with sophisticated type checking. Trying to pass a 1-dimensional array into a model that expects two dimensions? That’s a type error. Your editor can pick it up as the code leaves your fingers.
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. It's simple, clean, and it works for both research and production.
Small and easy to install with very few required dependencies, available on
conda for Linux, macOS and Windows. Simple source with a consistent API.
Thinc’s redesign is brand new, but previous versions have been powering spaCy since its release, putting Thinc into production in thousands of companies.
Neural networks have changed a lot over the last few years, and Python has too. Armed with new tools, Thinc offers a fresh look at the problem.