RuntimeError: Error(s) in loading state_dict for SyncNet_color: Missing key(s) in state_dict: "face_encoder.0.conv_block.0.weight",

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

10.28k stars 2.21k forks source link

RuntimeError: Error(s) in loading state_dict for SyncNet_color: Missing key(s) in state_dict: "face_encoder.0.conv_block.0.weight", #351

Open ayush714 opened 2 years ago

ayush714 commented 2 years ago

While running the below command,

%cd Wav2Lip/ 
!python hq_wav2lip_train.py --data_root /content/Wav2Lip/data_root/preprocessed/ --checkpoint_dir /content/drive/MyDrive/Technology/Ayushsproject/checkpoints --syncnet_checkpoint_path /content/drive/MyDrive/Technology/Ayushsproject/visual_quality_disc.pth

I am getting the following error,

sahilg06 commented 2 years ago

@ayush714, Actually its --syncnet_checkpoint_path and you are passing the path to another discriminator (visual quality), You should pass the path to syncnet (which is specifically trained for checking sync) not the visual quality one. This one.