tfyolo icon indicating copy to clipboard operation
tfyolo copied to clipboard

Weights for yolov5 & training loss

Open darkC00kie opened this issue 2 years ago • 3 comments

❔Looking for weights for yolov5 and how to minimize training loss

Are there existing weights which can be used ? And I have seen that you linked the weights from yolov4, do you have any advice on how to use them with this model?

Additionally what would you consider a "good" loss ? I currently have a loss of about 200 which seems a bit high and yields results wich are not that good. How can i improve my loss ? Thank you for your help!

darkC00kie avatar Jan 12 '22 12:01 darkC00kie

I also encountered the same problem. My loss is about 120. Have you finally solved it?

wang-zhix avatar Jan 24 '22 01:01 wang-zhix

Not yet, although even if the high loss still exists, the resluts look quite promisingto me. Are you also working with a custom data set ? And if so - did you manage to generate new anchors ?

darkC00kie avatar Jan 27 '22 19:01 darkC00kie

I'm train the yolo5m for 20 epoch with voc dataset, the latest loss about 200。When I run test.py with conf=0.3 and iou=0.1 ,the output is below: pred: person 0.3414 0 -83 500 416 bird 0.3518 0 -83 500 416 gt: horse 54.0 50.0 285.0 262.0 label: voc2022/JPEGImages/2007_000332.jpg 54.0,50.0,285.0,262.0,12 is there some bug in the test.py? How to soloe it? Look forward to your reply@LongxingTan @darkC00kie

whiterAutumn avatar Mar 11 '22 05:03 whiterAutumn