Tensor2Tensor: Open-Source Machine Learning Library for Research Tensor2Tensor is an open-source machine learning library developed by the TensorFlow team. It provides a wide range of tools for machine learning research, including implementations of various models, data sets, and algorithms. It also provides a user-friendly API to allow users to quickly and easily experiment with different models, techniques, and parameters. It is designed to be highly extensible, so that users can easily add new models and algorithms. Tensor2Tensor is widely used by researchers and developers in many areas, such as natural language processing, computer vision, and reinforcement learning.
https://github.com/tensorflow/tensor2tensor