physics-benchmarking-neurips2021
physics-benchmarking-neurips2021 copied to clipboard
Repo for "Physion: Evaluating Physical Prediction from Vision in Humans and Machines", presented at NeurIPS 2021 (Datasets & Benchmarks track)
- [x] Extract those trials where humans: (a) consistently succeed; (b) are close to chance; (c) systematically fail. _These can get passed into curiophysics for interestingness annotation._ - [x] More...
Hi, This is very impressive work! I believe it will be like ImageNet for Physicals prediction. However, I face many difficulties when I try to follow it. The problems are...
- [ ] move utils from `physion` to `physopt.model.utils`, clean up `physion` - [ ] Update dataprovider with new file structure - [ ] Document paths, naming of artifacts, make...
- [ ] Prep → checkpoint (6/18/21) → figure out what has to be done to get this up & running. - [ ] Writing custom wrapper to interface with...
Nice-to-figure-out: Sometimes need to refresh page a couple times to get it to load