batra-mlp-lab/visdial-challenge-starter-pytorch

This starter code is implemented using PyTorch v1.0, and provides out of the box support with CUDA 9 and CuDNN 7. There are two recommended ways to set up this codebase: Anaconda or Miniconda, and Docker. Note: Docker setup is necessary if you wish to extract image features using Detectron. We provide a Dockerfile which creates a light-weight image with all the dependencies installed. We recommend this development workflow, attaching the codebase as a volume would immediately reflect source code changes inside the container environment.