Giters

TimoBolkart / voca

This codebase demonstrates how to synthesize realistic 3D character animations given an arbitrary speech signal and a static character mesh.

Home Page:https://voca.is.tue.mpg.de/en

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Training with new Tensorflow Version

arefmalek opened this issue · comments

commented

Hello,

First off, thank you for the amazing work! I am trying to train the project on the VOCA set, and have been spending a lot of time trying to backtrack the old code from v1 into v2 (ran the tf_upgrade_v2 script and some more guesswork for the changes the script couldn't catch). I tried out the code from the branch dependabot/pip/tensorflow-gpu-2.12.0, and although the version is updated in requirements.txt , the code is still from v1 to my understanding.

Is there any work on making the code work in v2, all I have really been able to parse is this issue from 2021. Thanks!