default vqa2/mutan_att_train example (also for demo) is messed
Open
- Dominant language
- Python
- Stars
- 733
- Forks
- 176
- PR merge metrics
- No merged PRs in 30d
Description
Model from http://data.lip6.fr/cadene/vqa.pytorch/vqa2/mutan_att_train.zip gives extremely confusing results, I suggest everyone trying another model, e.g. http://webia.lip6.fr/~cadene/Downloads/vqa.pytorch/logs/vqa/mutan_att_trainval.zip which is on vqa (yaml is in vqa.pytorch/options/vqa/).
Contributor guide
No contributing guide indexed for this repository
Research direction
Start by checking the default VQA2/Mutan attention model reference and the YAML under vqa.pytorch/options/vqa/. Compare the model currently used by the example or demo with the suggested mutan_att_trainval.zip model. Done means the default example points to the working model and no longer produces the confusing results described.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, pytorch
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 2/5
- Estimated time
- 1-3 hours
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 35/100