how good performance do you get? (benchmark thread) about ultralytics

[glenn-jocher]

@LuminaDevelopment hi! Thanks for sharing details about your system and the inference time you're achieving with YOLOv8. Your setup with the RTX 4090 is quite powerful, and 9ms is an impressive inference speed! 🚀

Performance can vary based on several factors including the model variant used (e.g., YOLOv8n, YOLOv8x), the batch size, and the specific task (detection, segmentation, etc.). It might be interesting to see comparisons across different systems and setups from other users as well.

For those looking to benchmark their setup, the provided script is a great starting point. Just remember to adjust 'yolov8n.onnx' based on the model file you have and potentially explore using different image sizes via the imgsz parameter to see how it affects your inference times.

Feel free to share more insights or anything specific you find out during your benchmarks! 👍