openvinotoolkit / openvinotoolkit/open_model_zoo
c++ segmentation_demo is not functional
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 4.4k
- Forks
- 1.4k
- Avg merge
- 4d 13h
- Merged PRs (30d)
- 4
Description
c++ version of segmentation_demo does not produce segmentation mask. Mask is data is always all 0.
python version with same model and input file produces proper segmentation mask.
using OpenVINO [2024.5](version: 2024.5.0)
model: public\deeplabv3\PF16\deeplavv3.xml
input: video\head-pose-face-detection-male.mp4
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by comparing the C++ and Python segmentation_demo behavior with OpenVINO 2024.5, using public\deeplabv3\PF16\deeplavv3.xml and video\head-pose-face-detection-male.mp4. Trace how each demo produces its segmentation mask; done means the C++ demo produces a nonzero mask consistent with the Python version.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- cpp, python
- Domain
- computer-vision, machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 35/100