This is a web demo for camera-based PPG sensing (rPPG).

☕️ A vscode extension for netron, support *.pdmodel, *.nb, *.onnx, *.pb, *.h5, *.tflite, *.pth, *.pt, *.mnn, *.param, etc.

Layered Semantic Space Architecture

VSCode Extension of Type4Py

(computer vision in hosipitals) this is a simple rest api that classifies pneumonia infection weather it is Normal, Pneumonia Virus or Pneumonia Bacteria from a chest-x-ray image.

Digit recognition with dl4j

code generation chatbot for stabilty AIs stablecode

AI Image generator and NFT Creator

A library simplifying the work with TensorFlow.js in Node.

ml5.js example for ReactJS with Typescript variant. This repository contains two examples, one of pose-net and another of face-api. Read about this in my blog (https://analyticsindiamag.com/how-to-teach-machines-inside-a-browser/).

Deep learning framework for TypeScript

Different prototypes for detecting chemical graph presentation of the molecules into computer-readable format from image, IUPAC name

A simple implementation of a Multi-Layer Perceptron (MLP) neural network in TypeScript.使用 TypeScript 实现的简单多层感知器（MLP）神经网络。

AI-powered tool for early detection of nail-related diseases from images. Upload a nail photo and get real-time predictions using a high-accuracy deep learning model (97.8% accuracy). Built for scalability, efficiency, and healthcare accessibility.

Core TypeScript library for accessing the UFDL backend, managing the communication.

A showcase of my AI/ML journey—featuring hands-on projects in machine learning, deep learning, NLP, and real-world applications built using Python, TensorFlow, and more.

Spam comment detection on social media using emoji analysis and post-comment pair context to improve classification accuracy.

NeuroDetect AI is a deep-learning based system that detects brain tumors and Alzheimer’s disease from MRI scans using optimized CNN and transfer-learning models. It provides fast and reliable predictions through a simple web interface with a Flask backend, offering an effective AI solution for early neurological diagnosis.

Este projeto fornece a interface frontend responsável por interagir com a API de reconhecimento de dígitos manuscritos, permitindo ao usuário desenhar e visualizar os resultados da classificação. A aplicação integra o modelo de Deep Learning treinado com Keras/TensorFlow, utilizando o dataset público MNIST.