search

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

no checkpoint found ? #36

Open Mididou opened 4 years ago

Mididou commented 4 years ago

Hi , i'm trying to run the repo on Colab , this is the comman Line That entered:

! python test_all.py --test_root '/content/gdrive/My Drive/Talking-Face-Generation-DAVS-master/video' --test_type video --test_audio_video_length 848 --test_resume_path '/content/gdrive/My Drive/Talking-Face-Generation-DAVS-master/checkpoints/101_DAVS_checkpoint.pth.tar'

knowing that i have downloaded and loaded the checkpoints inside that file (they are effectively present).

Any help would be greatly appreciated , thank you.

molefeskymleya commented 4 years ago

Got the same error, and instead of python test_all.py --test_root ./0572_0019_0003/video --test_type video --test_audio_video_length 99 --test_resume_path CHECKPOINT_PATH, I ran python test_all.py --test_root ./0572_0019_0003/video --test_type video --test_audio_video_length 99 --test_resume_path checkpoints/101_DAVS_checkpoint.pth.tar.

Then it worked.

ZhengMengbin commented 4 years ago

@Mididou What's the meaning of the parameter --test_audio_video_length?

Mididou commented 4 years ago

Hi @ZhengMengbin , honestly , i don't recall anymore , i stopped digging a while ago , i'm really sorry .

ZhengMengbin commented 4 years ago

@Mididou I read the relevant code and know what it means. Thanks for your reply!