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
I think it is something like an indicator, which means the face will occupy 200200 pixels in the 256256 input image scale. The real scale factor is 1.25 in this code.
https://github.com/HRNet/HRNet-Facial-Landmark-Detection/blob/7b6c551bb53bbf0171ad536e3081ea465bb877dc/lib/datasets/cofw.py#L71
Could you explain what is the meaning of "200"? Thanks