Mohammed Innat

> Once you have the weights ready, feel free to ping me, @divyashreepathihalli, or @mattdangerw and we can get the weights uploaded to Kaggle. @mattdangerw Here are the weights files,...

@keras-team A gentle reminder for this PR. I would like to complete it within this month (if possible) after addressing the reviews. Otherwise please let me know if there are...

@divyashreepathihalli Thanks. I've written plenty of eample how to use this model with different backend, [link](https://github.com/innat/VideoSwin/tree/main/guides). For kaggle model page, could you please specify what and how much demonstration is...

@divyashreepathihalli Thanks for checking. Sorry for the inconveniences. I only checked with the tensorflow backend. I break down the key error. Let me know if I've missed anyting. - tensorflow...

About weight, please check [this](https://github.com/keras-team/keras-cv/pull/2369#issuecomment-1989420576). weight identifier ```bash a. kinetics400-tiny b. kinetics400-samll c. kinetics400-base d. kinetics400-base-imgnet22k f. kinetics600-base-imgnet22k g. something-something-v2-base ``` Each has its backbone and classifier part. comparision. I...

I think test are all passed. But eventually failling for this https://github.com/keras-team/keras-cv/pull/2401

Summarizing weight check. **Backbones** (tolerance 1e-4) - [notebook-1](https://www.kaggle.com/code/ipythonx/kerascv-torchvision-video-swin-logits-back) - [notebook-2](https://www.kaggle.com/code/ipythonx/k600-ssv2-logit-matching-torch-vs-keras-cv-back) **Classifier** (tolerance 1e-5) - [notebook-1](https://www.kaggle.com/code/ipythonx/kerascv-torchvision-video-swin-logits-comparison) - [notebook-2](https://www.kaggle.com/code/ipythonx/k600-ssv2-logit-matching-torch-vs-keras-cv) notebook-1 for kinetics-400 (tiny, small, base, base-imagenet22k) notebook-2 for kinetics-600 (base-imagenet22k), something-something-v2 @tirthasheshpatel...

# ONNX I noticed others also tried to export this model to onnx format but failed and reported to the official repo, [tickets](https://github.com/SwinTransformer/Video-Swin-Transformer/issues?q=is%3Aissue+is%3Aopen+onnx). So, I tried with this implementation with...

> lets move the video_swin layers into the model folder itself. Everything else LGTM! Sorry, could u please elaborate? Do u want [this](https://github.com/innat/keras-cv/blob/video_swin/keras_cv/layers/video_swin_layers.py) file to relocate to [here](https://github.com/innat/keras-cv/tree/video_swin/keras_cv/models/backbones/video_swin)? If so,...

I think the test is failling for other issue.