search

Rudrabha / Wav2Lip

This repository contains the codes of "A Lip Sync Expert Is All You Need for Speech to Lip Generation In the Wild", published at ACM Multimedia 2020. For HD commercial model, please try out Sync Labs
https://synclabs.so
9.8k stars 2.13k forks source link

color_syncnet_train.py videocard loaded but nothing going #102

Closed crankyz closed 3 years ago

crankyz commented 3 years ago

total trainable params 16435072 0it [00:00, ?it/s] i see only this message, made filelists/train.txt and val.txt but i'm not sure, is there should be only jpgs without audio, and is it matter about frame order, not i have something like this: /home/igor/Wav2Lip/l2/2/00003/0.jpg /home/igor/Wav2Lip/l2/2/00003/1.jpg /home/igor/Wav2Lip/l2/2/00003/10.jpg /home/igor/Wav2Lip/l2/2/00003/100.jpg

prajwalkr commented 3 years ago

The file lists format is wrong. It should be:

/home/igor/Wav2Lip/l2/2/00003/ --- a folder containing all frames of a video /home/igor/Wav2Lip/l2/2/00005/ --- another folder for another video