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

Providing checkpoints for pretrained semantic segmentation models #16

Open samar-fathallah opened 21 hours ago

samar-fathallah commented 21 hours ago

Hello there, In the paper it is mentioned that you trained the semantic segmentation models i.e. HRnet and SegFormer on cityscapes dataset augmented with diverse synthetic data generated by different methods. Are these pretrained models available anywhere for inference use (weights and checkpoints). I would like to adapt a similar evaluation approach for my task and it would be quite helpful to use those pretrained models. Thank you in advance.

YumengLi007 commented 14 hours ago

Hi @samar-fathallah , thanks for your interest!

Unfortunately, we are not able to release the segmentation related codes and models. But you could use mmsegmentation to train and test semantic segmentation models. We have released checkpoints for ALDM models, so you could generate new samples and train the segmenter with synthetic data.