Shivalika Singh
Shivalika Singh
### Model description Mask2Former is a single architecture for panoptic, instance and semantic segmentation. **Mask2Former Paper Abstract**: Image segmentation is about grouping pixels with different semantics, e.g., category or instance...
Hi, I have updated the video transformers example with links to model & space on Hugging Face hub. While trying to save and re-load the model, I faced few errors....
Hi, I have updated the ShiftViT example with links to model & space on Hugging Face Hub. (cc: @merveenoyan ) While working on setting up a demo space for ShiftViT,...
### What does this PR do? This PR adds Video Mask2Former model. Original repo: https://github.com/facebookresearch/Mask2Former/ Mask2Former for Video Instance Segmentation Paper: https://arxiv.org/abs/2112.10764 Co-authored with: @alaradirik - [x] Update model checkpoints...
### Feature request Hi, I went through optimum's code base and could not find support for object detection models. Is there plan to add ORTModelForObjectDetection just like ORTModelForImageClassification exists? Would...