PyTorch native quantization and sparsity for training and inference

Refine high-quality datasets and visual AI models

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

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

A framework for Smoothed Particle Hydrodynamics in Python

Rembg is a tool to remove images background

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

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

Turn any glasses into AI-powered smart glasses

Your Gateway to Embedded Software Development Excellence 👽

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

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

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

A simple way to calibrate your neural network.

A PyTorch Library for Multi-Task Learning

Open-source and strong foundation image recognition models.

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

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

Attention is all you need implementation

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

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…

VIP cheatsheets for Stanford's CS 229 Machine Learning

An offline library to reverse geocoding country names and ISO codes