Dipti Sengupta's Projects
Own copy to see how it works
A curated list of awesome Machine Learning frameworks, libraries and software.
Official code for the paper "Task2Vec: Task Embedding for Meta-Learning" (https://arxiv.org/abs/1902.03545, ICCV 2019)
Last 3 assignments for Bio Lab
This is the bulletinboard-ads sample application code used in the openSAP course: Cloud-Native Development with SAP Cloud Platform
All random bits of code written and not uploaded to its own repo
Optional competition for DL-WS2020/2021
Code for DL Labs.Old and New. Work in progress.
A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.
Config files for my GitHub profile.
A Swift port of the classic Gilded Rose refactoring kata
(partial) replication of results from https://arxiv.org/abs/1912.07768
Hacktoberfest Repo
Lab Materials for MIT 6.S191: Introduction to Deep Learning
Project with Jack Weitze
This repository contains a Pytorch implementation of the paper "The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks" by Jonathan Frankle and Michael Carbin that can be easily adapted to any model/dataset.
Lottery-ticket hypothesis primer. Simple implementation in Keras and TF.
Usable Implementation of "Bootstrap Your Own Latent" self-supervised learning, from Deepmind, in Pytorch
Paper implementations from scratch and machine learning tutorials
In-Database Machine Learning
Implementation network trimming using pytorch
[NeurIPS 2022] Official repository of paper titled "Bridging the Gap between Object and Image-level Representations for Open-Vocabulary Detection".
A repository in preparation for open-sourcing lottery ticket hypothesis code.
OpenEMS - Open Source Energy Management System
Machine Learning papers with code, data and models
Pretrained language model and its related optimization techniques developed by Huawei Noah's Ark Lab.
PyTorch Pruning Example
Pytorch implementation of the paper Exploring Simple Siamese Representation Learning.
Template for creating a Python Flask/Dash/Plotly single-page-application (SPA) for interactively charting IoT-type time series data stored in TimescaleDB (a PostgreSQL extension optimized for time-series data).