Should there be `models_predictions_tests` for all supported models?
Maintainers usually reply within 1 day
Nobody has claimed this yet.
Assessment
- Difficulty
- 5/5
- Estimated time
- Over a week
- Newbie friendliness
- 35/100
- Issue type
- Feature
- Clarity
- Needs clarification
- Activity status
- Active
- Tech stack
- python
- Domain
- machine-learning, testing
Research direction
Start by locating the existing models_predictions_tests and reviewing how they validate supported models. Confirm whether this remains the preferred validation approach, then define which model coverage is wanted, including YOLO v9, v11, v12, ResNet, or Qwen; done means an agreed scope and maintainers' guidance for potential PRs.
Written by the indexing model from the issue text.
Description
Search before asking
- I have searched the Inference issues and found no similar feature requests.
Question
Are models_predictions_tests still the preferred approach for new model validation? For example, would adding coverage for YOLO v9, v11, v12, ResNet, and Qwen models be useful?
Additional
I'm definitely still poking around this repo and am interested in trying things out with some models I've fine tuned. It would be great to understand your validation approaches for the widely used models so I can apply that to my use case! Also happy to submit PRs for a few of the models, especially the ones mentioned above or ones that you would find particularly useful.
- Dominant language
- Python
- Stars
- 2.5k
- Forks
- 340
- Avg merge
- 2d 11h
- Merged PRs (30d)
- 92
Getting set up
- No Dockerfile or Docker Compose file
- No pull request template
- Read the contributing 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.
More from roboflow/inference
-
Allow Pillow 13 in inference-sdkMay be free again A pull request for this issue was closed without being merged. Openbug
Difficulty 2/5 1-3 hours Newbie friendliness 80/100
roboflow/inference#3335 · 1 comment ·
Maintainers usually reply within 1 day
-
Difficulty 2/5 1-3 hours Newbie friendliness 66/100
roboflow/inference#3173 · 2 comments ·
Maintainers usually reply within 1 day
-
Difficulty 2/5 1-3 hours Newbie friendliness 78/100
roboflow/inference#2993 · 2 comments ·
Maintainers usually reply within 1 day
-
Add context manager (__enter__ / __exit__) support to InferencePipelinePossibly taken @KushagraKanaujia claimed this 67 days ago. Open
Difficulty 2/5 1-3 hours Newbie friendliness 76/100
roboflow/inference#2744 · 1 comment ·
Maintainers usually reply within 1 day
-
Difficulty 2/5 1-3 hours Newbie friendliness 68/100
roboflow/inference#1913 · 1 comment · 2 reactions ·
Maintainers usually reply within 1 day
All issues in roboflow/inference
Similar issues
-
area:core-platform effort:S priority:P3 risk:night-safe status:ready type:test
Difficulty 2/5 1-3 hours Newbie friendliness 78/100
randomparity/kdive#3620 ·
Maintainers usually reply within 1 day
-
Difficulty 2/5 1-3 hours Newbie friendliness 75/100
FinanceFlash/unvibecode#760 ·
Maintainers usually reply within 1 day
-
Difficulty 1/5 Under an hour Newbie friendliness 88/100
google-research/google-research#3470 ·
Maintainers usually reply within 21 days
-
Difficulty 2/5 1-3 hours Newbie friendliness 72/100
Maintainers usually reply within 1 day
-
Difficulty 1/5 Under an hour Newbie friendliness 88/100
mrvautin/ha-workouts#11 ·