Hello community! I am about to start a project where I'll be using Vision Transformers for prediction of next frame in video. I would like to know if there is a way to get started with vision transformers.
I am not familiar with Keras, Tensorflow, etc. What is the best way to get started? Shouls I jump straight into ViT? I know the theory, just need to get the code running!
Thank you very much. Any additional resources are appreciated.