search

Rudrabha / LipGAN

This repository contains the codes for LipGAN. LipGAN was published as a part of the paper titled "Towards Automatic Face-to-Face Translation".
http://cvit.iiit.ac.in/research/projects/cvit-projects/facetoface-translation
MIT License
585 stars 124 forks source link

May I ask how many GPU ram is needed? #15

Closed chikiuso closed 4 years ago

chikiuso commented 4 years ago

Hi @prajwalkr , I tried to run it on 1080 ti with 11 G gpu ram, however the system halt every time I run on GPU, May I ask how many GPU ram is needed? Thanks.

prajwalkr commented 4 years ago

Can you paste the detailed error log?

The model comfortably runs on an 11G GPU with around 64 batch size.

chikiuso commented 4 years ago

Thanks for your quick reply. It seems that it requires librosa installed, isn't it?

chikiuso commented 4 years ago

And may I ask how many G of Ram (not gpu) you have to run this project? thanks a lot!

prajwalkr commented 4 years ago

Thanks for your quick reply. It seems that it requires librosa installed, isn't it?

no, at the moment, I don't think we have used Librosa. We plan to do so in the future.

prajwalkr commented 4 years ago

And may I ask how many G of Ram (not gpu) you have to run this project? thanks a lot!

I am not sure about the exact numbers but the above statement that it can run on a single GPU is valid.

chikiuso commented 4 years ago

Hi @prajwalkr , sorry to keep asking questions ... I found the following error when running, thanks for your help! :

Using TensorFlow backend. Traceback (most recent call last): File "batch_inference.py", line 143, in from generator import create_model_residual as create_model File "/root/LipGAN/generator.py", line 14, in import librosa ImportError: No module named 'librosa'

chikiuso commented 4 years ago

I fix it by simply comment the import librosa, thanks :D