Angad's Projects
š Hi, Iām @angadbawa š Iām interested in Generative AI, Computer Vision, Machine Learning, Data Science š± Iām currently learning more about RAGs šļø Iām looking to collaborate on Machine Learning and Data Science Projects š« How to reach me Linkedin- https://www.linkedin.com/in/angadbawa/ Kaggle - https://www.kaggle.com/angadd
Roadmap to becoming an Artificial Intelligence Expert in 2022
:sparkles::sparkles:Latest Papers and Datasets on Multimodal Large Language Models, and Their Evaluation.
This research aims to predict the price of Bitcoin accurately, focusing on the direction of its price movement.
Custom Question Generator using T5 text-to-text transformer model and BoolQ dataset
Open-source project hosted at https://makeuseofdata.com to crowdsource a robust collection of notes related to data science (math, visualization, modeling, etc)
Drench yourself in Deep Learning, Reinforcement Learning, Machine Learning, Computer Vision, and NLP by learning from these exciting lectures!!
The aim of the experiment is to study the DNA in human and chimpanzees and classify the seven different types of proteins that are common in both humans and chimpanzees using the protein sequence data.
Me fiddling with docker
Pytorch code for our CVPRw 2023 paper "Cascaded Zoom-in Detector for High Resolution Aerial Images"
šāØ Help beginners to contribute to open source projects
A robot powered training repository :robot:
Ignitus technical stack data visualisation. šš»
Code release for paper "Incremental Learning of Object Detectors without Catastrophic Forgetting"
Intelligent Projects Using Python, published by Packt
Learn OpenCV : C++ and Python Examples
Your PyTorch AI Factory - Flash enables you to easily configure and run complex AI recipes for over 15 tasks across 7 data domains
The project aims to segment scenes in movies using a three-fold framework that combines shot segmentation, object detection, and object-based shot matching. It utilizes Convolutional Neural Networks (CNN) and set theory to accurately detect scene boundaries, providing a semantic-based navigation system for intuitive interaction with movies
š A list of open LLMs available for commercial use.
The project combines the "Segment Anything Model" (SAM) for interactive pixel selection and the "Stable Diffusion" model for inpainting based on user prompts, enabling users to create realistic image edits with a single click.