YOLOv5 image classification

[HKLCXQ]

Search before asking

• [X] I have searched the YOLOv5 issues and discussions and found no similar questions.

Question

Why can the input of image classification network only be pth weight file, can not modify the model, can only use the original yolov5n,s,m,l,x model

Additional

No response

[glenn-jocher]

@HKLCXQ the YOLOv5 image classification network currently supports input of only .pth weight files and uses the original YOLOv5n, s, m, l, x models. Modifying the model architecture directly is not currently supported. For more details, please refer to the Ultralytics Docs. If you have further questions, feel free to ask!

[github-actions[bot]]

👋 Hello there! We wanted to give you a friendly reminder that this issue has not had any recent activity and may be closed soon, but don't worry - you can always reopen it if needed. If you still have any questions or concerns, please feel free to let us know how we can help.

For additional resources and information, please see the links below:

• Docs: https://docs.ultralytics.com
• HUB: https://hub.ultralytics.com
• Community: https://community.ultralytics.com

Feel free to inform us of any other issues you discover or feature requests that come to mind in the future. Pull Requests (PRs) are also always welcomed!

Thank you for your contributions to YOLO 🚀 and Vision AI ⭐

[sunyongqi-04]

Try modifying your batch size to increase or decrease it

Search before asking

• [x] I have searched the YOLOv5 issues and discussions and found no similar questions.

Question

Why can the input of image classification network only be pth weight file, can not modify the model, can only use the original yolov5n,s,m,l,x model

Additional

No response

Try modifying your batch size to increase or decrease it

[glenn-jocher]

@sunyongqi-04 the input to the YOLOv5 image classification network is restricted to .pth weight files because the weights are tied to the specific architecture of the model they were trained on. Changing the model architecture would require retraining to generate new weights compatible with the modified structure. The YOLOv5 models (n, s, m, l, x) are predefined architectures that have been extensively tested and optimized for performance.

Regarding batch size, it can be adjusted in the training configuration to accommodate your system's memory constraints or to potentially improve training dynamics. However, this is unrelated to the ability to modify the model architecture itself. If you need guidance on how to adjust the batch size or other training parameters, please refer to the Ultralytics Docs. If you're looking to customize the model architecture, you might need to fork the repository and make your changes, keeping in mind that this requires a solid understanding of the model design and could affect performance.

[github-actions[bot]]

👋 Hello there! We wanted to give you a friendly reminder that this issue has not had any recent activity and may be closed soon, but don't worry - you can always reopen it if needed. If you still have any questions or concerns, please feel free to let us know how we can help.

For additional resources and information, please see the links below:

• Docs: https://docs.ultralytics.com
• HUB: https://hub.ultralytics.com
• Community: https://community.ultralytics.com

Feel free to inform us of any other issues you discover or feature requests that come to mind in the future. Pull Requests (PRs) are also always welcomed!

Thank you for your contributions to YOLO 🚀 and Vision AI ⭐