Hussam Lawen

T2TViT Performer backbone

1

Hey, Can I simply use performer (or other efficient transformers) in T2TViT similar to the original paper?

Latency Estimator (lookup table) & evolutionary search code neural-network-twins

1

Hey, thanks for your amazing work! can you share the Latency Estimator and the evolutionary search code based on the neural-network-twins to get a specialized sub-network? Thanks

LAION-FACE Dataset

2

Hi, Appreciate your work, 1. Are you planning on releasing the LAION-Face subset (metadata)? 2. You demonstrated that pretraining on LAION-Face improved 3 downstream tasks, I was wondering have you...

CelebA Multi-Task

3

Hey, Can you provide an example of how to train multi-task classification such as: - Visual Domain Decathlon - CelebA

I see that the Clean architecture doesn't include Android Data binding with MVVM pattern. MVVM is really powerfull especially when used it along with Data binding engine, and since Google...

What is the difference between `keypoints`, `skeleton` and `train_keypoints` and `train_skeletons` in the `config.yaml` file? If I wish to train on COCO keypoints (including eyes and ears...) should I edit...