Deep learning, machine learning marvels, and language sorcery in one repository :)

We write your reusable computer vision tools. 💜

SpideyX a multipurpose Web Penetration Testing tool with asynchronous concurrent performance with multiple mode and configurations.

TensorFlow 101: Introduction to Deep Learning

MiniLLM is a minimal system for running modern LLMs on consumer-grade GPUs

Quick exploration into fine tuning florence 2

Eye exploration

[I3D 2024] Deblur-GS: 3D Gaussian Splatting from Camera Motion Blurred Images

A Python interactive image zoom component for streamlit.

This repo consists of my implementation of DocFormerV2

【CVPR 2024 Highlight】Monkey (LMM): Image Resolution and Text Label Are Important Things for Large Multi-modal Models

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

Production-ready YOLO8 Segmentation deployment with TensorRT and ONNX support for CPU/GPU, including AI model integration guidance for Unitlab Annotate.

Implementation of https://srush.github.io/annotated-s4

Pujangga - Indonesian Natural Language Processing Tool with REST API, an Interface for InaNLP and Deeplearning4j's Word2Vec

Deepchecks' checks demo

[CVPR 2024 🔥] Grounding Large Multimodal Model (GLaMM), the first-of-its-kind model capable of generating natural language responses that are seamlessly integrated with object segmentation masks.

A small and simple python image processor to apply, view and save a variety of different image filters like threshold, brightness, contrast, blur, sharpen, dilate, erode, edge detection and mirror.…

Language Modeling with the H3 State Space Model

The Open Source DocuSign Alternative.

YOLOv8 object detection, tracking, image segmentation and pose estimation app using Ultralytics API (for detection, segmentation and pose estimation), as well as DeepSORT (for tracking) in Python. …

Inference Llama 2 in one file of pure C

Kode dan Data Wilayah Administrasi & Pulau Indonesia sesuai Kepmendagri No 100.1.1-6117 Tahun 2022 dengan PHP+MySQL+AJaX. Demo link : https://wilayah.cahyadsn.com/v2.6/

using duckdb to find insights about names and some other infos

A Jupyter widget for annotating images with bounding boxes

Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.

ICDAR 2019 Robust Reading Challenge on Scanned Receipts OCR and Information Extraction

Learn ML engineering for free in 4 months!