Ayush Thakur

neurips-llm-efficiency-challenge. Starter pack for NeurIPS LLM Efficiency Challenge 2023.

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

LossLandscape. 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.

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

3d-photo-inpainting. [CVPR 2020] 3D Photography using Context-aware Layered Depth Inpainting

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

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

wandb2kaggle. Automatically upload the model saved as W&B Artifact to Kaggle Dataset.

debugNNwithWandB. Concepts Explored in/with Pytorch

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

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

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

minimal-mlops. 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.

lit-gpt. 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.

grid-solver-with-obstacle. C++

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

T5-RLHF-TF. Implementation of Reinforcement Learning from Human Feedback for Summarization Task in TensorFlow

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

Awesome_DL_Links. Collection of awesome DL/Math resources to feel enlightened!

ayulockin. Pawan Kumar Portfolio

codingTrain-Data-API. Following this series : https://www.youtube.com/watch?v=tc8DU14qX6I

optimized_surveillance. For ECE Deptartment (Work in Progress)

AugMix_TF2. TF2.0 port for Augmix paper

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

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

deepgenerativemodeling. Towards Generative Modeling from (variational) Autoencoder to DCGAN

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

mmclassification. OpenMMLab Image Classification Toolbox and Benchmark

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

rpg-llm. A framework to play Divinity Original Sin 2

swe-agent. A simple SWE Agent for the SWE Benchmark

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

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

kaggle-asl. Jupyter Notebook

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

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

botbomb. C++

HF-RL-Course. My exploration and exploitation of HF-RL-Course