Tensors and Dynamic neural networks in Python with strong GPU acceleration

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

OpenAI Baselines: high-quality implementations of reinforcement learning algorithms

Post-training with Tinker

Assignments for CS294-112.

ChainerRL is a deep reinforcement learning library built on top of Chainer.

Code for reproducing key results in the paper "Improving Variational Inference with Inverse Autoregressive Flow"

A CMake-based build system that is used to build all packages in ROS.

Prototyping numpy arrays with named axes for data management.

Dense sift (Dsift) feature extraction using python and numpy.