Discover @ahsanmemon Open Source projects

Ahsan Memon (@ahsanmemon)

ahsanmemon

Stars
20
Global Rank 637,640 (Top 23 %)
Followers 21
Following 1
Registered over 7 years ago
Most used languages

Jupyter Notebook
80.0 %

Python
20.0 %
Location 🇵🇰 Pakistan
Country Total Rank 1,778
Country Ranking

Jupyter Notebook
166

Python
634

NFNets-Tensorflow

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

Unsupervised-Classification-Tensorflow

Jupyter Notebook

Transformer

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.