tensorflow: The 199k-star ML standard, from GPUs to Raspberry Pi

An end-to-end open-source platform for machine learning research and development. Developed by the Google Brain team for neural network research, it is now widely used to build and deploy ML applications across various domains.

It provides stable support for Python and C++ APIs, handling diverse hardware accelerations ranging from CUDA-based GPUs to macOS Metal and DirectX. Official builds allow execution on edge devices such as Raspberry Pi and Android.

It offers a rich ecosystem including the TensorBoard visualization tool and an official model library. Released under the Apache 2.0 license, it can be freely used in commercial projects, having established itself as an industry standard with over 190,000 stars.