Shoufa Chen
Shoufa Chen
Hello everyone, Thanks for your efforts in integrating DiffusionDet into awesome diffusers. We provided Swin-Base model here: https://github.com/ShoufaChen/DiffusionDet/releases/download/v0.1/diffdet_coco_swinbase.pth.
Hi, @345ishaan , May I ask about your progress on this integration? I am glad to offer help.
Hi, @345ishaan , You can leave the most challenging part to me since I think I am more familiar with DiffusionDet (as the author of this work).
Hi, Thanks for your interest. We didn't experiment with multiple nodes. I believe it can work with multiple nodes since our codebase is based on detectron2. You can refer https://github.com/facebookresearch/detectron2/issues/259...
Hi, Thanks for your interest. We have experimented with several `eta` values. The results demonstrate that `eta` has negligible influence on the final results. Therefore, we adopt `ddim_sampling_eta = 1.`...
Hi, Thanks for your interest. This data augmentation at the inference state is borrowed from Sparse R-CNN, Deformable DETR, and DETR. You can turn off this data augmentation to test...
Hi @abetlen Thanks for your help. I believe https://github.com/hwchase17/langchain/pull/2393 could help.
Hi, @yan-ctrl , please try again. I made it public.
`pip install -U transformers` solved my problem.
Kindly ping @alcinos @ashkamath I found a similar issue https://github.com/ashkamath/mdetr/issues/40. Any help would be much appriciated. Please let me know if you need further information.