An open protocol enabling communication and interoperability between opaque agentic applications.

PyTorch native quantization and sparsity for training and inference

An offline library to reverse geocoding country names and ISO codes

Attention is all you need implementation

Turn any glasses into AI-powered smart glasses

A PyTorch Library for Multi-Task Learning

Efficient vision foundation models for high-resolution generation and perception.

This library augments road images to introduce various real world scenarios that pose challenges for training neural networks of Autonomous vehicles. Automold is created to train CNNs in specific w…

[CVPR 2024] Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data. Foundation Model for Monocular Depth Estimation

Refine high-quality datasets and visual AI models

A distilled Segment Anything (SAM) model capable of running real-time with NVIDIA TensorRT

Open-source and strong foundation image recognition models.

A quick and simple tool for labeling images, videos and time series data, right from Jupyter!

A framework for Smoothed Particle Hydrodynamics in Python

HDF5 for Python -- The h5py package is a Pythonic interface to the HDF5 binary data format.

A Python package for handling spherical polygons that represent arbitrary regions of the sky

Rembg is a tool to remove images background

A simple way to calibrate your neural network.

Your Gateway to Embedded Software Development Excellence 👽

VIP cheatsheets for Stanford's CS 229 Machine Learning

YOLOv4 / Scaled-YOLOv4 / YOLO - Neural Networks for Object Detection (Windows and Linux version of Darknet )

🛠 All-in-one web-based IDE specialized for machine learning and data science.

A (PyTorch) imbalanced dataset sampler for oversampling low frequent classes and undersampling high frequent ones.