You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I have two questions regarding your implementation:
In the Implementation Details section of the Appendix, you mention training a diffusion model (citing the DDPM paper) for both COCO and CityScapes datasets. Do you plan to release these model weights, perhaps on HuggingFace? This would be a valuable resource for researchers interested in this topic.
I noticed your codebase builds upon VTA, which currently provides segmentation scripts only for ImageNet. Would it be possible to share the segmentation test code for COCO and CityScapes datasets as well. Also could you explicitely provide links for which variation of COCO (https://cocodataset.org/#download) and CitySpace you are refering to.
The text was updated successfully, but these errors were encountered:
Great work!
I have two questions regarding your implementation:
In the Implementation Details section of the Appendix, you mention training a diffusion model (citing the DDPM paper) for both COCO and CityScapes datasets. Do you plan to release these model weights, perhaps on HuggingFace? This would be a valuable resource for researchers interested in this topic.
I noticed your codebase builds upon VTA, which currently provides segmentation scripts only for ImageNet. Would it be possible to share the segmentation test code for COCO and CityScapes datasets as well. Also could you explicitely provide links for which variation of COCO (https://cocodataset.org/#download) and CitySpace you are refering to.
The text was updated successfully, but these errors were encountered: