Hangz-nju-cuhk / Talking-Face-Generation-DAVS

Code for Talking Face Generation by Adversarially Disentangled Audio-Visual Representation (AAAI 2019)
MIT License
818 stars 173 forks source link

face_align #55

Open HITxyer opened 4 years ago

HITxyer commented 4 years ago

hi, thank you for your sharing. It's profitable for me, in face_align.py, I wound not understand how this points is generated points = [[70, 112], [110, 112], [90, 150]] I am looking forward to your reply, thank you.

HITxyer commented 4 years ago

Supplement: Points2= np.array (points) scale in face_align.py.
for points = [[70, 112],[110, 112],[90, 150]], is it generated in256
256? If yes , pointsscale = [[140, 224],[220, 224],[180, 300]], Out of range256256. I am sorry not to understand it.