Sayak Paul's Projects
Implemented an A/B Testing solution with the help of machine learning
This project presents a simple framework to retrieve images similar to a query image.
Contains additional materials for two keras.io blog posts.
Includes additional materials for the following keras.io blog post.
Minimal implementation of adaptive gradient clipping (https://arxiv.org/abs/2102.06171) in TensorFlow 2.
This repository contains notebooks that show the usage of TensorFlow Lite for quantizing deep neural networks.
Shows how to create basic image adversaries, and train adversarially robust image classifiers (to some extent).
Contains my experiments for the Kaggle competition "Aerial Cactus Identification"
The repository contains my experiments for a Hackathon problem by Analytics Vidhya
A simple REST API based on this repository:
A simple web app for age detection based on a Hackathon problem by Analytics Vidhya
A simple Python project for playing with anagrams.
Contains my analysis of a database containing information about the students of an engineering college.
Contains my experiments for the Game of Deep Learning Hackathon conducted by Analytics Vidhya
Contains my assignments, guiding notebooks (provided as the course materials) and the datasets.
The problem goes way back to 1999 when Yann LeCun came up with this phenomenal dataset. I had my CNN introduction with this very dataset. This submission was a part of this: https://datahack.analyticsvidhya.com/contest/practice-problem-age-detection/ .
TensorFlow implementation of Barlow Twins (https://arxiv.org/abs/2103.03230).
Contains benchmarking and interpretability experiments on the Adult dataset using several libraries
Contains my experiments made with the mighty library BentoML
Compares the DistilBERT and MobileBERT architectures for mobile deployments.
Contains my experiments with the `big_vision` repo to train ViTs on ImageNet-1k.
This repository hosts the code to port NumPy model weights of BiT-ResNets to TensorFlow SavedModel format.
This project demonstrates the use of TensorFlow Object Detection API (along with GCP ML Engine) to automatically detect Red Blood Cells (RBCs), White Blood Cells (WBCs), and Platelets in each image taken via microscopic image readings
Repository to test automated PyPI publishing through GitHub Actions.
Experiments to show the usage of deep learning to detect breast cancer from breast histopathology images
Implementation of CaiT models in TensorFlow and ImageNet-1k checkpoints. Includes code for inference and fine-tuning.
This repository implements the idea of "caption upsampling" from DALL-E 3 with Zephyr-7B and gathers results with SDXL.
Contains my code and deck for Cloud Community Days Ahmedabad 2022.
This repository holds files and scripts for incorporating simple CI/CD practices for model training in ML.
PyTorch implementation of CLIP Maximum Mean Discrepancy (CMMD) for evaluating image generation models.