search

boschresearch / ALDM

Official implementation of "Adversarial Supervision Makes Layout-to-Image Diffusion Models Thrive" (ICLR 2024)
https://yumengli007.github.io/ALDM/
GNU Affero General Public License v3.0
52 stars 3 forks source link

Inquiry about GPU Training Time #14

Closed huamiao1012 closed 5 months ago

huamiao1012 commented 5 months ago

Thank you for your incredible work！I would like to ask about the GPU training time required for the model. Additionally, could you please provide guidance on how to find the evaluation functions for mIOU and FID?

YumengLi007 commented 5 months ago

Hi @huamiao1012 , thanks for your interests! The model is trained with 2 A100 for 3-5 days depending on the dataset size. For FID evaluation, we used the implementation here. For mIoU evaluation, we used pretrained DRN and UperNet101 segmentation networks for Cityscapes and ADE20K dataset, respectively.

huamiao1012 commented 5 months ago

Thank you for your reply! I got it.