search

kpzhang93 / MTCNN_face_detection_alignment

Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Neural Networks
MIT License
2.8k stars 1.01k forks source link

evaluation result is different from the paper #23

Open sarah-zhu opened 6 years ago

sarah-zhu commented 6 years ago

I evaluated the author's model on WIDER FACE dataset. The result is different from the paper. I set minsize as 10, scale factor as 0.79 and threshold as [0.5 0.5 0.3]. paper's result evaluation result using author's model
easy set: 85.1 83.3 medium set: 82 80.9 hard set: 60.7 62.2

Has anyone reproduced the author's performance on WIDER FACE?

LinnaWang76 commented 6 years ago

你好！你是怎么做的reproduce!我用onet 得到的bbox和score ，参数也跟你一样，可是结果比你的差很多……

oliviawindsir commented 4 years ago

@sarah-zhu do you mind sharing how did you generate the easy/medium/hard set dataset?