Wang Ao

@xenova Thanks! We cleared the cache by refreshing the page with disabling the cache in devtool. We then test your image in the demo and the result is below. Strangely,...

@xenova Thanks a lot for your detailed explanation and great help! It works now! Thank you very much! ❤️ 

Thanks for your interest! Does this issue #128 help?

Please feel free to reopen this issue if you have further questions.

Thanks for your interest! You could detect a live video like this ``` wget https://storage.openvinotoolkit.org/repositories/openvino_notebooks/data/data/video/people.mp4 yolo predict model=yolov10s.pt source=people.mp4 conf=0.1 ```

Thanks for your interest! Could you please provide the details of what correct predictions mean?

Since there is no NMS in the postprocessing, we can directly output the `max_det` predictions. > In yolov8, using `save_txt` flag will only save the final results of the prediction(results...

Thanks. Due to that the model does not need NMS, all output predictions can be directly added into the validator without the threshold.

Thanks. Do you calculate mAP in the same way as COCO?

Thanks. Could you please provide more details of how you use the same command as COCO to calculate mAP? Do you save the `predictions.json` and call `eval_json` to calculate the...