LFFD-A-Light-and-Fast-Face-Detector-for-Edge-Devices icon indicating copy to clipboard operation
LFFD-A-Light-and-Fast-Face-Detector-for-Edge-Devices copied to clipboard

头部检测问题

Open jun214384468 opened this issue 4 years ago • 6 comments

如何用头部检测模型测试自己的图片呢?一直找不到

jun214384468 avatar Jan 07 '21 03:01 jun214384468

(yjh_torch) yan@whyhowinfo:~/yjh_work/LFFD/head_detection/accuracy_evaluation$ python predict.py Traceback (most recent call last): File "predict.py", line 264, in run_prediction_pickle() File "predict.py", line 224, in run_prediction_pickle from config_farm import configuration_10_160_17L_4scales_v1 as cfg ModuleNotFoundError: No module named 'config_farm'

jun214384468 avatar Jan 07 '21 03:01 jun214384468

就像这种的 为换成绝对路径from ..config_farm import configuration_10_160_17L_4scales_v1 as cfg也是不行

jun214384468 avatar Jan 07 '21 03:01 jun214384468

您好,没有测试但张图片的Demo吗

jun214384468 avatar Jan 07 '21 03:01 jun214384468

您的人脸和人头检测效果极差啊

yzl1014 avatar Feb 05 '21 07:02 yzl1014

@yzl1014 人脸是用WIDERFACE训练的,应该在大多数情况下是可以是用没问题的。人头的检测不能在其他场景是用,需要用自己的数据进行训练。

YonghaoHe avatar Feb 05 '21 07:02 YonghaoHe

@YonghaoHe @jun214384468 能否提供一个人头检测的ONNX模型,便于在其他框架中测试

lf2020 avatar Mar 18 '21 06:03 lf2020