roboflow / roboflow/roboflow-python
Result of `model.predict` has type `ClassificationModel`, no keypoints.
Open
Nobody has claimed this yet.
bug
- Dominant language
- Python
- Stars
- 629
- Forks
- 140
- Avg merge
- 2d 2h
- Merged PRs (30d)
- 5
Description
Tested on several projects:
- Glue tube keypoints: https://app.roboflow.com/model-examples/glue-tube-keypoints
- Football pitch recognition below.
pip install supervision roboflow
version = rf.workspace("roboflow-jvuqo").project("football-field-detection-f07vi").version(8)
version.download("yolov8")
kp_model = version.model
assert kp_model is not None
first_image_path = os.listdir(f"{dataset.location}/train/images")[0]
first_image_path = f"{dataset.location}/train/images/{first_image_path}"
result = kp_model.predict(first_image_path).json()
# Fails
keypoints = sv.KeyPoints.from_inference(result)
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
Reproduce the report with the supplied pip install command and football-field model example, then inspect the result of kp_model.predict(first_image_path).json(). Compare that output with the input expected by sv.KeyPoints.from_inference(result); done means the keypoint inference result is represented so this call no longer fails.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- computer-vision, machine-learning
- Issue type
- Bug
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 35/100