search

YonghaoHe / LFFD-A-Light-and-Fast-Face-Detector-for-Edge-Devices

A light and fast one class detection framework for edge devices. We provide face detector, head detector, pedestrian detector, vehicle detector......
MIT License
1.31k stars 330 forks source link

头部检测问题 #102

Open jun214384468 opened 3 years ago

jun214384468 commented 3 years ago

如何用头部检测模型测试自己的图片呢？一直找不到

jun214384468 commented 3 years ago

(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 commented 3 years ago

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 commented 3 years ago

您好，没有测试但张图片的Demo吗

yzl1014 commented 3 years ago

您的人脸和人头检测效果极差啊

YonghaoHe commented 3 years ago

@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。

lf2020 commented 3 years ago

@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