PyTorch native quantization and sparsity for training and inference

Cataloging released Triton kernels.

Web viewer for ontologies written in Graphol

Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

A Lightweight Face Recognition and Facial Attribute Analysis (Age, Gender, Emotion and Race) Library for Python

Tool for producing high quality forecasts for time series data that has multiple seasonality with linear or non-linear growth.

Describes the full end to end smart parking application that is available with DeepStream 5.0

Robyn is an experimental, AI/ML-powered and open sourced Marketing Mix Modeling (MMM) package from Meta Marketing Science. Our mission is to democratise modeling knowledge, inspire the industry thr…

Python Computer Vision & Video Analytics Framework With Batteries Included

Source code for Twitter's Recommendation Algorithm

Curated list of open source tooling for data-centric AI on unstructured data.

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…

Official PyTorch implementation of StyleGAN3

Getting started with diffusion

DeepStream SDK Python bindings and sample applications

[ICCV'21] UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstruction

A Unified Framework for Surface Reconstruction

Out-of-the-box code and models for CMU's object detection and tracking system for multi-camera surveillance videos. Speed optimized Faster-RCNN model. Tensorflow based. Also supports EfficientDet. …

This is a sample application for counting people entering/leaving in a building using NVIDIA Deepstream SDK, Transfer Learning Toolkit (TLT), and pre-trained models. This application can be used to…

A DeepStream sample application demonstrating end-to-end retail video analytics for brick-and-mortar retail.

SPIGA: Shape Preserving Facial Landmarks with Graph Attention Networks.

Pretrain, finetune ANY AI model of ANY size on multiple GPUs, TPUs with zero code changes.

Instant neural graphics primitives: lightning fast NeRF and more

MONAI Tutorials

Framework agnostic sliced/tiled inference + interactive ui + error analysis plots

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

Bridging Knowledge Graphs to Generate Scene Graphs, ECCV 2020

YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite