Muhammed Swalihu

icon location London icon location A quick learner with a strong technical background and analytical mindset, achieved first-class honors in MSc Intelligent Systems.

Results 4 comments of Muhammed Swalihu

Improving object detection benchmarking process for unrelated datasets

Hi! I’d like to work on this enhancement. I have experience building benchmarking tools for ML pipelines and can help extend the `supervision` toolkit to support robust object detection evaluations...

Add BenchmarkEvaluator with basic precision/recall computation

Hi @SkalskiP @onuralpszr — I've submitted this PR for the BenchmarkEvaluator (Issue #1778 ). Let me know if you'd like me to fix the `pre-commit` error or extend this further....

Add BenchmarkEvaluator with basic precision/recall computation

Hi @soumik12345 , thanks for the review! I’ll go ahead and: Replace the placeholder logic in BenchmarkEvaluator with full precision/recall/mAP computation, Add a working demo example (maybe in a Colab...

Add BenchmarkEvaluator with basic precision/recall computation

Hi @soumik12345, I've added a Colab-style demo notebook BenchmarkEvaluator_Demo.ipynb! It includes: - How to import and use the BenchmarkEvaluator - Per-class precision and recall visualization - A visual example comparing...