answer about keypoint_detector.py

zhanglonghao1992 / One-Shot_Free-View_Neural_Talking_Head_Synthesis

Pytorch implementation of paper "One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencing"

Other

782 stars 143 forks source link

Closed hongju-jeong closed 2 years ago

hongju-jeong commented 2 years ago

Line 173

yaw = self.fc_roll(out)
pitch = self.fc_pitch(out)
roll = self.fc_yaw(out)  
t = self.fc_t(out)           
exp = self.fc_exp(out)

why yaw is fc_roll? why roll is fc_yaw?

zhanglonghao1992 commented 2 years ago

@muzy06038 The layer name is wrong, but it doesn't matter :)

hongju-jeong commented 2 years ago

Thank you!