search

HRNet / HRNet-Facial-Landmark-Detection

This is an official implementation of facial landmark detection for our TPAMI paper "Deep High-Resolution Representation Learning for Visual Recognition". https://arxiv.org/abs/1908.07919
MIT License
1.04k stars 264 forks source link

The effect of scale, center_w, center_h on performance? #43

Open booyoungxu opened 4 years ago

booyoungxu commented 4 years ago

Thanks for you code! But the annoying thing is that scale, center_w, center_h are needed when inference. Whether there are substitutable transformations without scale, center_w, center_h? Or how much of an impact does while preprocessing with scale, center_w, center_h? Looking forward to a reply, thanks~

mucunwuxian commented 4 years ago

@booyoungxu I think... It is necessary to estimate the landmark after cropping the face part. It is the same when learning. Therefore, the accuracy cannot be guaranteed unless the same crop as during learning is performed during estimation. (Do not deviate from the learning conditions.)

ref : https://github.com/HRNet/HRNet-Facial-Landmark-Detection/issues/3