zay comments

Results 20 comments of

zay

val/obj loss and val/box loss keep raising in the training of yolo pose with coco dataset

> @gadewegit en, The val loss curve is ascending. And lr curve

val/obj loss and val/box loss keep raising in the training of yolo pose with coco dataset

@gadewegit emmm, I'm trying it out ..

val/obj loss and val/box loss keep raising in the training of yolo pose with coco dataset

> > @gadewegit emmm, I'm trying it out .. > > 好的，希望我们保持联系。 @gadewegit Hi, I finetuned a model with coco dataset and custom dataset(1/4 percent，but only simple samples, person background...

val/obj loss and val/box loss keep raising in the training of yolo pose with coco dataset

> Oh, I'm glad to hear that you have solved some problems. Do obj loss, box loss, and learning rate curves appear normal? May I have a look at your...

val/obj loss and val/box loss keep raising in the training of yolo pose with coco dataset

> @gadewegit Could you attach your train command line code and train & val curve？

val/obj loss and val/box loss keep raising in the training of yolo pose with coco dataset

@gadewegit github text format error

val/obj loss and val/box loss keep raising in the training of yolo pose with coco dataset

> @gadewegit what's your train hyp parameters, eg: python train.py --data data/coco_kpts.yaml --cfg cfg/yolov7-w6-pose.yaml --weights weights/yolov7-w6-pose.pt --batch-size 16 --img 640 --kpt-label --device 0 --name aaaa --hyp data/hyp.pose.yaml --epochs 300 --workers...

val/obj loss and val/box loss keep raising in the training of yolo pose with coco dataset

> > > > > > > > > @gadewegit 你的训练参数是什么，例如：python train.py --data data/coco_kpts.yaml --cfg cfg/yolov7-w6-pose.yaml --weights weights/yolov7-w6-pose.pt --batch-size 16 --img 640 --kpt-label --device 0 --name aaaa --hyp data/hyp.pose.yaml --epochs...

val/obj loss and val/box loss keep raising in the training of yolo pose with coco dataset

@gadewegit you can set lr0:0.001, and change the train.py blow:

install.sh安装报错subprocess.CalledProcessError: Command '['cmake', '--build', '.', '--verbose', '--parallel=52']' returned non-zero exit status 2.

same problem cuda 12.3 python 3.11 torch 2.4.1