Wang Ao

Thanks for your interest! Yes, it is supported. You could specify the `imgsz` argument for training.

Yes, it is [height, weight].

Thanks for your interest! You could specify `batch` when inferring a dataset in batch, like ``` yolo predict model=yolov10s.pt batch=2 ``` For multi-GPU inference, does this issue https://github.com/ultralytics/ultralytics/issues/3953 help?

Does that mean continuing training on COCO? > Thank you for your reply，another question is about how to resume yolov10 rather than finetuning?

Thanks. You could specify the `model` and `resume` argument, like below ```python from ultralytics import YOLOv10 model = YOLOv10('epoch_10.pt') model.train(resume=True) ```

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

Thanks for your interest! Could you please provide more details of how to reproduce this issue? For example, what's the original size of the input image?

Thank you very much for your contribution! Could you please add the paperspace notebook along with the colab demo and remove the ipynb files? Thank you!

Thanks! Could you please add the paperspace notebook link and remove the newly added ipynb files? Thank you!

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