Discover ahsanmemon/Transformer Open Source project

Stars
2
Language
License
MIT License
Created over 4 years ago
Updated about 4 years ago

ahsanmemon

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

This repo will contain code on the transformer architecture that I have coded in Tensorflow 2. I will try and make sure there are some easy-to-use jupyter notebooks available too and some training scripts that would help test its functionality relatively easily.

NFNets-Tensorflow

Python

GANs

Venturing into GANs with a focus on creating completely custom models ultimately.

Jupyter Notebook

Triplet-Loss

My efforts to understand and implement the Triplet Loss Function

Jupyter Notebook

Gradient-Tape

Creating custom routines in Tensorflow has never been easy. Mostly because of the complexities involved in writing the code. With tensorflow 2.0 eager-execution and GradientTape, I find it relatively easier to write models while avoiding the confusing sub-classing APIs that Tensorflow provides. This repository contains some of the code that I wrote to understand and implement models using GradientTape instead of the classical model.fit or model.compile methods that Keras and Tensorflow 2 provide.

Jupyter Notebook

Cool-Research-and-Courses