Training time on FFHQ - Githubissues

taesungp / swapping-autoencoder-pytorch

Official Implementation of Swapping Autoencoder for Deep Image Manipulation (NeurIPS 2020)

Other

512 stars 86 forks source link

Training time on FFHQ #21

Closed VitoChien closed 2 years ago

VitoChien commented 2 years ago

Thanks for sharing your awesome work. I'm trying to reproduce the results of FFHQ and I want to know how long it takes to train the pretrained models of FFHQ. Thanks~

taesungp commented 2 years ago

Hello, it takes about 2 weeks at 1024x1024 resolution on 8-V100 GPU machine.

asheroin commented 2 years ago

Would you please share the training time under various dataset/training settings described in your paper or just update thoes information in READMD.md? It would be very helpful for people follwing these works.