NVIDIA-ISAAC-ROS / NVIDIA-ISAAC-ROS/isaac_ros_image_segmentation
isaac_ros_segment_anything parameter setting is not working
Nobody has claimed this yet.
- Dominant language
- C++
- Stars
- 127
- Forks
- 16
- PR merge metrics
- No merged PRs in 30d
Description
I have been working with isaac_ros_segment_anything. For now, everything works great in the example. However, I tried to change some parameters to enhance the result. I have changed the parameters
-
mask_width
-
mask_height
-
max_batch_size
under the node SegmentAnythingDecoderNode and also changed the parameters -
prompt_input_type
-
has_input_mask
-
max_batch_size
under the node SegmentAnythingDataEncoderNode by usingros2 param setcommand. It was saying 'Set parameter successful'. However, nothing changed at all in the results.
I thought maybe I should run isaac_ros_segment_anything_triton.launch.py, but it was not even working at all. Can you tell me how to change those parameters? I basically want to define a bounding box in my region of interest, but I cannot change anything.
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 reviewing the SegmentAnythingDecoderNode and SegmentAnythingDataEncoderNode parameter sections linked in the issue, then reproduce the behavior with ros2 param set. Check isaac_ros_segment_anything_triton.launch.py as the reported alternative entry point. Done means determining why the listed parameters do not affect results and documenting or correcting how bounding-box prompts and other settings are applied.
Written by the indexing model from the issue text.
Assessment
- Domain
- ai, computer-vision
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 30/100