facebookresearch / facebookresearch/detectron2
visualize_json_results.py IndexError: too many indices for tensor of dimension 1
- Dominant language
- Python
- Stars
- 34.7k
- Forks
- 7.9k
- PR merge metrics
- No merged PRs in 30d
Description
## Instructions To Reproduce the 🐛 Bug:
I use visualize_json_results.py to visualize the results for faster rcnn on lvis_v0.5_val dataset, however I can only get results for 12 pictures and get the following error:
## Expected behavior:
I want to get the visualization results for every picture in lvis_v0.5_val dataset.
## Environment:
detectron2_v0.1.1
Contributor guide
Research direction
Start with visualize_json_results.py and reproduce the failure using Faster R-CNN results on the lvis_v0.5_val dataset under detectron2 v0.1.1. Inspect the traceback at the tensor indexing operation after the first 12 images, then verify the script can produce visualization results for every picture in the dataset.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- computer-vision
- Issue type
- Bug
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 35/100