search

mehdidc / feed_forward_vqgan_clip

Feed forward VQGAN-CLIP model, where the goal is to eliminate the need for optimizing the latent space of VQGAN for each input prompt
MIT License
136 stars 18 forks source link

training GPU configuration #23

Open CrossLee1 opened 2 years ago

CrossLee1 commented 2 years ago

Thanks for your excellent repo.

When training cc12m_32x1024 with type VitGAN or MLP Mixer, what kinds of GPU environment do you use? Tesla V100 with 32G mem or others?

Thanks

mehdidc commented 2 years ago

So I guess similar answer here @CrossLee1, see issue #21. For the GPU it's A100s with 40GBs.