search

protossw512 / AdaptiveWingLoss

[ICCV 2019] Adaptive Wing Loss for Robust Face Alignment via Heatmap Regression - Official Implementation
Apache License 2.0
395 stars 88 forks source link

what is output dimention? #15

Closed aligoglos closed 4 years ago

aligoglos commented 4 years ago

Its obvious input dimension of model is 256256. but it seems output landmarks aren't fit to 256 256 for example result of them on image is like this: test

mustangchavez commented 4 years ago

I had trouble with that at first, too. The output landmarks are 64x64, the architecture of the network uses a lower resolution output than input.

aligoglos commented 4 years ago

thanks.