Rishit Dagli

A TensorFlow/ Keras implementation of Nystromformer, a transformer variant that uses the Nyström method to approximate standard self-attention with O(n) complexity which allows for better scalability.

This repo implements Fastformer: Additive Attention Can Be All You Need by Wu et al. in TensorFlow. Fast Transformer is a Transformer variant based on additive attention that can handle long sequences efficiently with linear complexity. Fastformer is much more efficient than many existing Transformer models and can meanwhile achieve comparable or even better long text modeling performance.

A TensorFlow/Keras implementation of the Transformer in Transformer paper for image classification, attention inside local patches: pixel-level attention paired with patch level attention

Use just 2 lines of code to instantly improve your model training performance on certain tasks by upto 70% and moderate training time and generalization improvements! Implements Gradient Centralization in TensorFlow and makes it availaible as a Python Package to easily use it.

A TensorFlow/Keras implementation of Conformer which achieves the best of both worlds: transformers for content-based global interactions and CNNs to exploit local features

This project implements DeepMind's new Perceiver Model: General Perception with Iterative Attention in TensorFlow which solves the Transformers Quadratic compute and memory bottleneck.

This repo implements Geoffrey Hinton's latest paper GLOM in TensorFlow, which allows advances made by several different groups transformers, neural fields, contrastive representation learning, distillation and capsules to be combined.

This repository demonstrates how you can get started with on-device ML with tools or plugins specifically launched with Android 11 with example Android Apps too!

This repo shows how one could get started using Firebase ML Kit in their Flutter app very easily, showing an example of implementing Face Recognition using Firebase ML Kit in a sample Flutter app.