Stable release for VisDial challenge 2019.
This tag links to the official released code for VisDial challenge 2019. It does not preserve backward compatibility with v2018
.
What's new with v2019
?
- Almost a complete rewrite of v2018, which increased speed, readability, modularity, and extensibility.
- Multi-GPU support - try out specifying GPU ids to train/evaluate scripts as: --gpu-ids 0 1 2 3
- Docker support - we provide a Dockerfile which can help you set up all the dependencies with ease.
- Stronger baseline - our Late Fusion Encoder is equipped with Bottom-up Top-Down attention. We also provide pre-extracted image features (links below).
- Minimal pre-processed data - no requirement to download tens of pre-processed data files anymore (were typically referred to as visdial_data.h5 and visdial_params.json).