TDI's Projects
Locally run an Instruction-Tuned Chat-Style LLM
For training Alpaca
This project is a Computer Vision implementation of general hierarchical pattern discovery principles introduced in README
Espressif's Voice Assistant SDK: Alexa, Google Voice Assistant, Google DialogFlow
Falcon LLM with Chat UI using LangChain and Chainlit
Saves lot of time by explaining logically whether your chosen Github repo is best fit for your problem, analyses code automatically, gives you step by step instruction to run the code,also attempts to explain code in simple terms and mathematical reasoning behind this,
GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration.
Liquid Warping GAN with Attention: A Unified Framework for Human Image Synthesis
Learn OpenCV : C++ and Python Examples
truck stockpile volume cal from Intel Realsense Lidar -L515 Series
New ways of breaking app-integrated LLMs
Models and examples built with TensorFlow
trying to make all academic records of students at one place ( marks in maths ,science English ) from class 1 till 12. also capture their Iq aq,cq,eq along with family details , health issues etc
nbconvert as a web service: Render Jupyter Notebooks as static web pages
Open3D: A Modern Library for 3D Data Processing
Universal API for request permission and get its statuses.
Python package for point cloud registration using probabilistic model (Coherent Point Drift, GMMReg, SVR, GMMTree, FilterReg, Bayesian CPD)
pyntcloud is a Python library for working with 3D point clouds.
https://www.youtube.com/channel/UC34rW-HtPJulxr5wp2Xa04w?sub_confirmation=1
Retrieval Augmented Generation using openai, streamlit, langchain and Pinecone
Some Random Quick Codes that can Help others
Adult Chat App
[ICML'24] SeeAct is a system for generalist web agents that autonomously carry out tasks on any given website, with a focus on large multimodal models (LMMs) such as GPT-4V(ision).
Botpress Spades
Program calculates the speed of vehicle with any angle and also works for night time. Program auto calculates the detection range for different speed of vehicle. COSINE CORRECTION has been implimented in code, accuracy tested on GROUND TRUTH VIDEO For daytime is 98% in Km/Hr