Paula Derrenger

@BugOOM 对于极端比例的物体，YOLOv8目前可能存在检测不足的情况。这是一个很好的观察，我们会持续改进模型以解决这个问题。感谢你的反馈，我们会关注这个问题并努力改进模型的性能。

@Zigars i understand your frustration. The `FileNotFoundError: [Errno 2] No such file or directory: 'runs/detect/train/weights/best.pt'` issue has been a point of concern among users. I recommend that you try using...

@Zengyf-CVer you're welcome! If you have any more questions or run into any other issues, feel free to ask. Happy coding!

@lukazso it appears that the issue might be related to a mismatch between the installed version of PyTorch and the running version of CUDA. When encountering the "CUDA error: CUBLAS_STATUS_INVALID_VALUE"...

@darouwan it's unfortunate that you're encountering this CUDA error while training YOLOv8 on rectangular images. The issue might not be directly related to the number of classes, as the error...

@alicera yes, you can also use the Python command directly without the YOLOv8 CLI by importing the `train` module from YOLOv8 and calling the necessary functions in your Python script....

@dmddmd currently, there isn't a scientific paper detailing the YOLOv8 architecture. However, the architecture and functionalities of YOLOv8 are detailed in the Ultralytics documentation. If you need specific details for...

@sstainba thanks for the update! It's great to hear that the issue seems to have been resolved. If you encounter any further issues or have additional feedback, feel free to...

@theotherp hey there! It looks like you're encountering an issue with your training and validation process in YOLOv8. I'd be happy to help you out with this. From the information...

@takyq apologies for the confusion. The issue seems to be related to the conversion of the trained model to tflite. We are actively working on improving the export functionality, including...