search

biubug6 / Face-Detector-1MB-with-landmark

1M人脸检测模型(含关键点)
MIT License
1.02k stars 271 forks source link

Inference Speed and Precision on edge device #7

Open hegc opened 4 years ago

hegc commented 4 years ago

When the input size is 320*240, the speed of Face-Detector is higher than MTCNN's, but the results of AP of retinaface-m0.25 will be lower than MTCNN's on WIDERFACE-val.

When the input size is 640*480, the results of AP of retinaface-m0.25 will be lower than MTCNN's on WIDERFACE-val, but the speed of Face-Detector is lower than MTCNN's.

How do you think these models inference on edge device?

biubug6 commented 4 years ago

Generally speaking, retinaface-m0.25 is faster than MTCNN under the same effect on edge device. You can show accurate accuracy and time between retinaface0.25 and MTCNN on widerface val used for referential purpose only.

hegc commented 4 years ago

em...MTCNN results on Widerface val: Easy Val AP: 0.8311434383349002 Medium Val AP: 0.8108204487059174 Hard Val AP: 0.5786071147566203 , but I think the comparison maybe is not fair.

hegc commented 4 years ago

Can we make tracking mode on retina-face? If the detector has detected one face, then it just need to look around the face at next frame.