vincent-thevenin / Realistic-Neural-Talking-Head-Models

My implementation of Few-Shot Adversarial Learning of Realistic Neural Talking Head Models (Egor Zakharov et al.).
GNU General Public License v3.0
828 stars 195 forks source link

Generate Noises #52

Closed zyainfal closed 3 years ago

zyainfal commented 4 years ago

Hi, thanks for your work on reproducing this paper.

During the test, I ran the embedder_inference.py, without fine-tuning, and ran video_inference.py but I got a noise output from models. test

Any suggestions? Thanks!

zhaoyuehrb commented 3 years ago

Same here... Did you solve it? Thanks!

zhaoyuehrb commented 3 years ago

Remove the '*255' for out1 in video_reference.py near the end. Then the output will be normal. Cheers!

zyainfal commented 3 years ago

Remove the '*255' for out1 in video_reference.py near the end. Then the output will be normal. Cheers!

Sorry for this late reply. But it is great! Cheers!