shahman0605 Goto Github PK

captionwiz-image-captioning-with-transformers

Unlock the power of AI to add context and depth to your images with CaptionWiz, a cutting-edge image captioning solution based on state-of-the-art Transformers. Generate captivating and informative captions for your visual content effortlessly

evalplus

EvalPlus for rigourous evaluation of LLM-synthesized code

gpt4v-browsing

Web Scraping with GPT-4 Vision API and Puppeteer

image_manipulation_detection_system

ImageForgeryDetect is an advanced image manipulation detection system designed to identify copy-move and splicing forgeries with high accuracy. Leveraging deep learning, image processing algorithms, and other methodologies, this project offers a robust solution for detecting manipulated images. The system provides class-wise classification accuracy

james-webb-telescope-simulation

The simulation works out the so-called restricted three-body problem where an small object, such as an asteroid or satellite, is interacting with two large objects, such as the Sun and the Earth, through Newtonian gravity.

mlx

MLX: An array framework for Apple silicon

mlx-examples

Examples in the MLX framework

molecular-dynamics-simulations

This Project explores the dynamics of molecules within a gas as they move in time. We ask the question, that what is the different trajectories of these molecules with time as an parameter and using periodic boundary conditions.

neuromorphic_learning

Machine Learning tools for Dynamic Vision Sensors such as DVS128

pix2structr

google/pix2struct-docvqa-base

screenshot-to-code

Drop in a screenshot and convert it to clean code (HTML/Tailwind/React/Vue)

self-operating-computer

A framework to enable multimodal models to operate a computer.

similollm

vimgpt

Browse the web with GPT-4V and Vimium

vocode-python

🤖 Build voice-based LLM agents. Modular + open source.