Ayush Thakur

TensorFlow implementation of "Unsupervised Learning of Visual Features by Contrasting Cluster Assignments".

Explores the ideas presented in Deep Ensembles: A Loss Landscape Perspective (https://arxiv.org/abs/1912.02757) by Stanislav Fort, Huiyi Hu, and Balaji Lakshminarayanan.

Starter pack for NeurIPS LLM Efficiency Challenge 2023.

Deep Image Inpainting using UNET like Vanilla Autoencoder and Partial Convolution based Autoencoder.

[CVPR 2020] 3D Photography using Context-aware Layered Depth Inpainting

Generating Digital Painting Lighting Effects via RGB-space Geometry (SIGGRAPH2020/TOG2020)

Implementation of modern data augmentation techniques in TensorFlow 2.x to be used in your training pipeline.

Automatically upload the model saved as W&B Artifact to Kaggle Dataset.

Concepts Explored in/with Pytorch

Custom Keras Callbacks for Feature Visualization, Class Activation Map, Grad-CAM

Helpful data preprocessing, training, and visualisation code and scripts for a range of Kaggle competitions, supported by Weights & Biases.

A simple repository showcasing a few LLM Evaluation strategies and leverages W&B Sweeps to optimize the LLM system.

This repository is for the GDG Cloud Kolkata workshop on 27th August, 2022. Learn about minimal MLOps required for any ML practitioner. It uses Weights and Biases.

Hackable implementation of state-of-the-art open-source LLMs based on nanoGPT. Supports flash attention, 4-bit and 8-bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.

Simple FastAPI server on top of ChromaDB

No description.

Repo for our talk at GDG Kolkata TensorFlow All Round event on 31st August.

Implementation of Reinforcement Learning from Human Feedback for Summarization Task in TensorFlow

This repository contains notebooks exploring various aspects of High-Performance Large-Scale Image RecognitionWithout Normalization (https://arxiv.org/abs/2102.06171).)

Collection of awesome DL/Math resources to feel enlightened!

Pawan Kumar Portfolio

This will contain my basic Deep Learning experiments. It's just a pool.

Following this series : https://www.youtube.com/watch?v=tc8DU14qX6I

TF2.0 port for Augmix paper

For ECE Deptartment (Work in Progress)

Towards Generative Modeling from (variational) Autoencoder to DCGAN

Classification pipeline for Kaggle Pogchamp Series competition built using TF/Keras and W&B.

OpenMMLab Image Classification Toolbox and Benchmark

This repo will contain my implementation of AlphaGO and related experiments.

This repository contains arduino code for our bot which was capable of detecting blocks(cubes) using IR sensor and distinguish between two block sizes.

A framework to play Divinity Original Sin 2

A simple SWE Agent for the SWE Benchmark

A set of scripts and notebooks on LLM finetunning and dataset creation

Implementation of Masked Siamese Networks for Label-Efficient Learning (https://arxiv.org/abs/2204.07141) in TensorFlow.

No description.

OpenMMLab Semantic Segmentation Toolbox and Benchmark.

Example deep learning projects that use wandb's features.

OpenMMLab Detection Toolbox and Benchmark

A simple Replit to train a classifier using PyTorch on a toy dataset with baked in goodness of Weights and Biases.

Solution to all the potential questions for DS practical lab exam

No description.

Contain the talks given

Contains notebook used during my Pandas session.

Exploring LLMs by implementing and understanding all the key components, perform experiments and optimize it.

The NVIDIA Agent Intelligence Toolkit (AIQ Toolkit) is an open-source library for efficiently connecting and optimizing teams of AI agents.

A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)

A query language for programming (large) language models.

No description.

My exploration and exploitation of HF-RL-Course

This is a collection of short Python scripts to solve and automate tasks and simplify any work.

Semantic and drivable segmentation for autonomous driving using Keras and baked with Weights and Biases.

🔥 A tool for visualizing and tracking your machine learning experiments. This repo contains the CLI and Python API.

Repository of my experiments for the Kaggle competition: Happywhale - Whale and Dolphin Identification

No description.

Source code for xfields (SIGGRAPH Asia 2020)

ECCV'20 paper `In-Domain GAN Inversion for Real Image Editing` code (PyTorch version)

[Python 3] Tensorflow implementation of "Show, Attend and Tell: Neural Image Caption Generation with Visual Attention"

Detectron2 is FAIR's next-generation platform for object detection and segmentation.

No description.

This repository will contain my thought experiments conducted in the field of Deep Learning.

Understanding with depth

Personal website of Ayush Thakur 👉

Framework for evaluating and improving agents

A toy simulation for the greatest artificial organisms of our plannet

A benchmark for LLMs on complicated tasks in the terminal

Weave is a toolkit for developing AI-powered applications, built by Weights & Biases.

Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, Replicate, Groq]

Verifiers for LLM Reinforcement Learning

No description.

Student version of Assignment 1 for Stanford CS336 - Language Modeling From Scratch

LlamaIndex (GPT Index) is a data framework for your LLM applications

Agent Reinforcement Trainer for training multi-turn agents using GRPO

Train transformer language models with reinforcement learning.

Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.

Educational material for workshops

Random stuffs

No description.

Guardrails-Genie is a tool that helps you implement guardrails in your LLM applications.

Holistic Evaluation of Language Models (HELM), a framework to increase the transparency of language models (https://arxiv.org/abs/2211.09110). This framework is also used to evaluate text-to-image models in Holistic Evaluation of Text-to-Image Models (HEIM) (https://arxiv.org/abs/2311.04287).

Supercharge Your LLM Application Evaluations 🚀

Adding guardrails to large language models.

Inspect: A framework for large language model evaluations

An end-to-end image classification pipeline in TensorFlow done correctly. This is supplementary resource of TFUG Mumbai May Meetup.

For a Kaggle competition: Learning Agency Lab - Automated Essay Scoring 2.0

No description.

Fun manim based animations.

The official evaluation suite and dynamic data release for MixEval.

Demo repository for llamaindex webinar (10/07/24)

Pretrain, finetune and deploy AI models on multiple GPUs, TPUs with zero code changes.

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

A framework for few-shot evaluation of autoregressive language models.

No description.

Supplementary source code for our half day training session at ODSC 23 on end to end MLOps

Minimal implementation of GPT-2 in TensorFlow

Reach a target phrase using genetic algorithm

Weights & Biases Addons is a repository consisting of additional unitilities and community contributions for supercharging your Weights & Biases workflows.

A Large-Scale Semantic and Emotional Multi-Modal Dataset for Conversational Gestures Synthesis [ECCV 2022]

Trying to push the accuracy on FashionMNIST dataset without using pre-trained weights and by training for 20 epochs only.

Used for adaptive human in the loop evaluation of language and embedding models.

Autonomously follow wall using IR sensor

YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite

A repo showcasing SMSL and W&B

Industry-strength Computer Vision workflows with Keras

No description.

DALL·E Mini - Generate images from a text prompt

🌊 Online machine learning in Python

No description.

(ICLR 2022 Spotlight) Official PyTorch implementation of "How Do Vision Transformers Work?"

A unified, comprehensive and efficient recommendation library

No description.

Code release for ConvNeXt model

Unoffical implementation about Image Super-Resolution via Iterative Refinement by Pytorch

Site built from fastpages: https://fastpages.fast.ai/. Deployed here 👉

A modular framework for vision & language multimodal research from Facebook AI Research (FAIR)

Fork of http://sourceforge.net/projects/mjpg-streamer/

Trying out nbdev

PyTorch implementation of paper "Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenes"

No description.

ECCV'20 paper `In-Domain GAN Inversion for Real Image Editing` code

Mining Discriminative Components with Random Forests

Repository for Synthetic datasets I'm creating

compilation of various numerical methods, a decipline of mathemathics.

Short wandb reports showcasing simple DL cocepts, tools and tasks.

[CVPR2020] Adversarial Latent Autoencoders

Keras implementations of Generative Adversarial Networks.

Keras implementation of the "Show, Attend and Tell" paper

Unofficial implementation of "Image Inpainting for Irregular Holes Using Partial Convolutions". Try at: www.fixmyphoto.ai

TensorFlow User Group Kolkata website

PyTorch Tutorial for Deep Learning Researchers

Detect faces in an image and give prediction about the age, ethnicity and emotion of that face.

Repository for an article for weights and biases

Repository for resources in Intro to ML with DSC NSEC YouTube Live Course

How to train a TensorFlow Object Detection Classifier for multiple object detection on Windows

Easy hyperparameter optimization and automatic result saving across machine learning algorithms and libraries

Codes for the experiments conducted in DSP Lab.

Awesome Object Detection based on handong1587 github: https://handong1587.github.io/deep_learning/2015/10/09/object-detection.html

No description.

No description.

This repository is for anyone who is new to image processing and is super excited by the topic.

Plotly's Documentation

Online recognition of American Sign Language Finger Spelling from a video (webcam) and interpretation of the gestures.

Development of a self balancing robot using arduino and GY-521 breakout board

Data Structure in C

List of Computer Science courses with video lectures.

Heart sound segmentation code based on duration-dependant HMM

A series of Jupyter notebooks that walk you through the fundamentals of Machine Learning and Deep Learning in python using Scikit-Learn and TensorFlow.

Python Implementation of Reinforcement Learning: An Introduction

Face recognition using Tensorflow

DeepTraffic is a deep reinforcement learning competition, part of the MIT Deep Learning series.

List of Data Science Cheatsheets to rule the world

Papers with code. Sorted by stars. Updated weekly.

Think DSP: Digital Signal Processing in Python, by Allen B. Downey.

Fast and flexible AutoML with learning guarantees.

A traffic counter designed using the OpenCV library for Python 3.5. This project was carried out as part of the Government Data Science Accelerator programme

Road traffic simulator and signals optimizer in CoffeeScript & HTML5

JavaScript 3D library.

Shortest path to reach the end of maze

Here i have collected my own created haar cascade. Hope you will find it useful.

Models and examples built with TensorFlow

Open Source Computer Vision Library

FAIR's research platform for object detection research, implementing popular algorithms like Mask R-CNN and RetinaNet.

Maze Solver Robot, using Artificial Intelligence with Arduino

A variety of algorithms to solve mazes from an input image

A neural network bot for Make