Mohammed Innat

YOLO-V7 https://github.com/keras-team/keras-cv/issues/1179

cc. @Joker316701882 @FateScript Mentioning some authors of the [YOLOX](https://arxiv.org/abs/2107.08430) to give some valuabe comments here. [YOLOX-Docx.](https://yolox.readthedocs.io/en/latest/) - [YOLOX-Code](https://github.com/Megvii-BaseDetection/YOLOX)

Supporting this might be useful. Usually `onnx` is needed to convert to torch model to tf-lite. So supporting this from Keras-Core might be effective. However, [`torch.onnx.export`](https://pytorch.org/docs/stable/onnx.html) exist.

I think this should be added to the Keras-io website. This way it will reach and attract more users.

@sachinprasadhs > If you encounter a KerasCV feature that is missing from KerasHub, or would like to propose an addition to the library, please file [an issue with KerasHub](https://github.com/keras-team/keras-hub/issues). Firstly,...

The reconstruction approach is shown in[ this](https://github.com/innat/VideoMAE/blob/main/notebooks/reconstruction.ipynb) file. Let mke if you have query afterward.

@divyashreepathihalli Thanks for the confirmation. I pulled out the movinet from tf-model garden and maintaining to a dedicated repo (private for now). The codebase somewhat complex due to large number...

@sachinprasadhs > If you encounter a KerasCV feature that is missing from KerasHub, or would like to propose an addition to the library, please file [an issue with KerasHub](https://github.com/keras-team/keras-hub/issues). Firstly,...

**TODO** Components - [ ] [Swin Transformer](https://github.com/keras-team/keras-cv/issues/671) - [ ] Mult-scale Deform Attention, [official-gdino](https://github.com/IDEA-Research/GroundingDINO/blob/2b62f419c292ca9c518daae55512fabc3fead4a4/groundingdino/models/GroundingDINO/ms_deform_attn.py#L136), [mmcv](https://github.com/open-mmlab/mmcv/blob/master/mmcv/ops/multi_scale_deform_attn.py), [official](https://github.com/fundamentalvision/Deformable-DETR/blob/main/models/ops/modules/ms_deform_attn.py) - [ ] [DeformableTransformerEncoder/DecoderLayer](https://github.com/IDEA-Research/GroundingDINO/blob/2b62f419c292ca9c518daae55512fabc3fead4a4/groundingdino/models/GroundingDINO/transformer.py#L738C7-L738C40) - [ ] [BiAttentionBlock](https://github.com/IDEA-Research/GroundingDINO/blob/2b62f419c292ca9c518daae55512fabc3fead4a4/groundingdino/models/GroundingDINO/fuse_modules.py#L252) (Bi-Direction MHA (text->image, image->text))

@tirthasheshpatel The https://github.com/keras-team/keras-cv/pull/2319 is about video-swin modelling, and I think the grounding-dino (g-dino) needs image-swin model, so this [issue](https://github.com/keras-team/keras-cv/issues/671) needs to be progressed first as a prerequisite of current issue....