Hengyuan Hu

bottom-up-attention-vqa. An efficient PyTorch implementation of the winning entry of the 2017 VQA Challenge.

rainbow. A PyTorch implementation of Rainbow DQN agent

ibrl. Python

instruct-rl. Python

jax-vs-pytorch. Python

a2c. Python

monometis. Python

dem. Building deep energy models

nogil-pybind. C++

pytorch-a2c-ppo-acktr. PyTorch implementation of Advantage Actor Critic (A2C), Proximal Policy Optimization (PPO) and Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation (ACKTR).

optim-weight-norm. Python

res-hans. Evaluate cleverhans(https://github.com/openai/cleverhans) on deep residual nets.

asd. Python

merge-segments. merge segments besed on their margins orientation