YOLOv6-Face

[oussaifi-majdi]

Before Asking

• [X] I have read the README carefully. 我已经仔细阅读了README上的操作指引。

• [X] I want to train my custom dataset, and I have read the tutorials for training your custom data carefully and organize my dataset correctly; (FYI: We recommand you to apply the config files of xx_finetune.py.) 我想训练自定义数据集，我已经仔细阅读了训练自定义数据的教程，以及按照正确的目录结构存放数据集。（FYI: 我们推荐使用xx_finetune.py等配置文件训练自定义数据集。）

• [X] I have pulled the latest code of main branch to run again and the problem still existed. 我已经拉取了主分支上最新的代码，重新运行之后，问题仍不能解决。

Search before asking

• [X] I have searched the YOLOv6 issues and found no similar questions.

Question

i tried to use YOLOv6-Face to detect faces in image but i can't find any example to use this model

Additional

No response

[Chilicyy]

Hi, you can switch to yolov6-face branch, and refer to readme. By the way, if you want to test yolov6-face n/s/m/l models, code from tag 0.3.1 should be used, while you want to test yolov6-face-lite models, code from tag 0.4.0 should be used. We're arranging the code to be compatible with both versions of the models lately.

[oussaifi-majdi]

thank you for the speed of the answer but I try to follow readme but I find this error AttributeError: Can't get attribute 'SimConv' on <module 'yolov6.layers.common' from 'C:\Users\Lenovo\PycharmProjects\yolo6\YOLOv6\yolov6\layers\common.py'>

[Chilicyy]

hi, if you want to test yolov6-face n/s/m/l models, code from tag 0.3.1 should be used, while you want to test yolov6-face-lite models, code from tag 0.4.0 should be used. Just use git checkout 0.3.1 to switch to certain version.

[oussaifi-majdi]

PS C:\Users\Lenovo\PycharmProjects\yolo6\YOLOv6> python C:\Users\Lenovo\PycharmProjects\yolo6\YOLOv6\tools\infer.py --weights C:\Users\Lenovo\PycharmProjects\yolo6\YOLOv6\yolov6l_face.pt --source C:\Users\Lenovo\Desktop\widerface\images\valid --yaml C:\Users\Lenovo\Desktop\widerface\data.yaml --conf 0.02 --not-save-img --save-txt-widerface --name widerface_yolov6l Namespace(agnostic_nms=False, classes=None, conf_thres=0.02, device='0', half=False, hide_conf=False, hide_labels=False, img_size=[640, 640], iou_thres=0.45, max_det=1000, name='widerface_yolov6l', not_save_img=True, project='runs/inference', save_dir=None, save_txt=False, save_txt_widerface=True, source='C:\Users\Lenovo\Desktop\widerface\images\valid', view_img=False, webcam=False, webcam_addr='0', weights='C:\Users\Lenovo\PycharmProjects\yolo6\YOLOv6\yolov6l_face.pt', yaml='C:\Users\Lenovo\Desktop\widerface\data.yaml') Loading checkpoint from C:\Users\Lenovo\PycharmProjects\yolo6\YOLOv6\yolov6l_face.pt

Fusing model... Switch model to deploy modality. 100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 324/324 [13:53<00:00, 2.57s/it] PS C:\Users\Lenovo\PycharmProjects\yolo6\YOLOv6> cd widerface_evaluate cd : Cannot find path 'C:\Users\Lenovo\PycharmProjects\yolo6\YOLOv6\widerface_evaluate' because it does not exist. At line:1 char:1

• cd widerface_evaluate

• 
  + CategoryInfo          : ObjectNotFound: (C:\Users\Lenovo...erface_evaluate:String) [Set-Location], ItemNotFoundException
  + FullyQualifiedErrorId : PathNotFound,Microsoft.PowerShell.Commands.SetLocationCommand

PS C:\Users\Lenovo\PycharmProjects\yolo6\YOLOv6>

[Chilicyy]

Hi @oussaifi-majdi , we have updated pretrained weights matching for the latest code. Please git pull the latest code on main branch, and download pretrained weights from 4.0 release page.

[oussaifi-majdi]

I try to find a simple face detection code with yolo-face-lite but I can't find it so I do the steps from https://github.com/meituan/YOLOv6/blob/yolov6-face/README.md but still i have the same error

[Chilicyy]

Hi, we have updated pretrained weights matching for the latest code. Please git pull the latest code on main branch, and download pretrained weights from 4.0 release page.