Why there is large difference in mAP value on Raspberry Pi 4 and normal server for the same trained model?

[jaskiratsingh2000]

Hey! I am trying to test the Accuracy Performance that is the mAP value of yolov5 on Raspberry Pi 4.

I trained the pre-trained yolov5s model with the following parameters on the server and with the value of the weights I got, I tested those on the Raspberry Pi for the Accuracy Performance:

• data - coco.yaml
• weights - yolov5s.pt
• batch - 50
• epochs - 300
• cfg - yolov5s.yaml

by following this command -> python3 train.py --data coco.yaml --batch 50 --epochs 300 --weights yolov5s.pt --cfg yolov5s.yaml

but when I transfer the weights file and test the mAP value on raspberry pi with those weights file I am getting 0.000032 mAP value whereas if I test the same weights file on the server I get the mAP value as 0.68.

The computer is a computer then why there is such a large difference in the mAP value that is Accuracy performance on Raspberry Pi 4?

@glenn-jocher Please let me know if you have any idea about this?
Thanks!

[jaskiratsingh2000]

@glenn-jocher @batrlatom Please let je know if you have any idea about this as I have been trying to know this past few months and kinda stuck here so please let me know. Would highly appreciate that. Thanks!!

[github-actions]

👋 Hello, this issue has been automatically marked as stale because it has not had recent activity. Please note it will be closed if no further activity occurs.

Access additional YOLOv5 🚀 resources:

• Wiki – https://github.com/ultralytics/yolov5/wiki
• Tutorials – https://docs.ultralytics.com/yolov5
• Docs – https://docs.ultralytics.com

Access additional Ultralytics ⚡ resources:

• Ultralytics HUB – https://ultralytics.com
• Vision API – https://ultralytics.com/yolov5
• About Us – https://ultralytics.com/about
• Join Our Team – https://ultralytics.com/work
• Contact Us – https://ultralytics.com/contact

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 YOLOv5 🚀 and Vision AI ⭐!