facebookresearch / facebookresearch/detectron2
Please read & provide the following
- Dominant language
- Python
- Stars
- 34.7k
- Forks
- 7.9k
- PR merge metrics
- No merged PRs in 30d
Description
If you do not know the root cause of the problem, please post according to this template:
## Instructions To Reproduce the Issue:
Hello, I'm running the CondInst model which is based on detectron2. The program web is
https://github.com/aim-uofa/AdelaiDet
When I was testing, I wanted to see how the model worked, but the code I wrote in the forward() method of such as "exit()" and "print()" didn't execute. I suspect this is related to the registration mechanism of detectron2. what should I do ?
Check https://stackoverflow.com/help/minimal-reproducible-example for how to ask good questions.
Simplify the steps to reproduce the issue using suggestions from the above link, and provide them below:
1. Full runnable code or full changes you made:
```
python demo/demo.py \
--config-file configs/CondInst/MS_R_50_3x.yaml \
--input ./imgs/ \
--output output_images/CondInst/CondInst_MS_R_50_3x \
--confidence-threshold 0.35 \
--opts MODEL.WEIGHTS pretrained_models/CondInst/CondInst_MS_R_50_3x
```
2. What exact command you run:
no
3. __Full logs__ or other relevant observations:
```
```
## Expected behavior:
project stop and exit.
## Environment:
detectron2 0.2.1
fvcore 0.1.1.post20200716
torch 1.5.0
torchvision 0.6.0a0+82fd1c8
Paste the output of the following command:
```
wget -nc -nv https://github.com/facebookresearch/detectron2/raw/main/detectron2/utils/collect_env.py && python collect_env.py
```
If your issue looks like an installation issue / environment issue,
please first check common issues in https://detectron2.readthedocs.io/tutorials/install.html#common-installation-issues
Contributor guide
Research direction
Start by running the provided demo/demo.py command with configs/CondInst/MS_R_50_3x.yaml and the stated environment. Inspect the forward() method of adet.modeling.condinst.condinst.CondInst and the registration path, then document whether execution reaches it. Done requires a minimal reproducible command, full logs, and a confirmed explanation of the observed behavior.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- computer-vision, machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100