An Implementation of Transformer in Transformer in TensorFlow for image classification, attention inside local patches
Why do you think that https://github.com/LogicalAtomist/principia is a good alternative to Transformer-in-Transformer
An Implementation of Transformer in Transformer in TensorFlow for image classification, attention inside local patches
Why do you think that https://github.com/LogicalAtomist/principia is a good alternative to Transformer-in-Transformer