Neural Magic is excited to share that we’ve sparsified YOLOv5 for a 10x increase in performance and 12x smaller model files. You can now use tools and integrations linked from the YOLOv5 model page to:
- Reproduce our benchmarks
- Train YOLOv5 on new datasets to replicate our performance with your own data.
We also wrote a blog that speaks to our methodology and digs deeper into benchmarking numbers. Let us know what you think!
– Team Neural Magic