fandulu

llama3-from-scratch

llama3 implementation one matrix multiplication at a time

minbpe

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

recognize-anything

Open-source and strong foundation image recognition models.

maplab

A Modular and Multi-Modal Mapping Framework

autodistill

Images to inference with no labeling (use foundation models to train supervised models).

FoundationPose

[CVPR 2024 Highlight] FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects

Metric3D

The repo for "Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image" and "Metric3Dv2: A Versatile Monocular Geometric Foundation Model..."

Bunny

A family of lightweight multimodal models.

OpenSeeD

[ICCV 2023] Official implementation of the paper "A Simple Framework for Open-Vocabulary Segmentation and Detection"

cuspatial

CUDA-accelerated GIS and spatiotemporal algorithms

CameraCalibration

Fisheye or Normal Camera Intrinsic and Extrinsic Calibration. Surround Camera Bird Eye View Generator.

june

Local voice chatbot for engaging conversations, powered by Ollama, Hugging Face Transformers, and Coqui TTS Toolkit

MegaParse

File Parser optimised for LLM Ingestion with no loss 🧠 Parse PDFs, Docx, PPTx in a format that is ideal for LLMs.

concept-graphs

Official code release for ConceptGraphs

dino-tracker

Official Pytorch Implementation for “DINO-Tracker: Taming DINO for Self-Supervised Point Tracking in a Single Video”

PAMI

PAMI is a Python library containing 100+ algorithms to discover useful patterns in various databases across multiple computing platforms. (Active)

pose2sim

Markerless kinematics with any cameras — From 2D Pose estimation to 3D OpenSim motion

multi-hmr

Pytorch demo code and models for Multi-HMR

leapvo

[CVPR'24] LEAP-VO: Long-term Effective Any Point Tracking for Visual Odometry

search-agents

Code for the paper 🌳 Tree Search for Language Model Agents

EgoVideo

[CVPR 2024 Champions] Solutions for EgoVis Chanllenges in CVPR 2024

awesome-multi-robot-system

Recent multi-robot projects and papers: Including SLAM, place recognition, Large Language Models navigation. (continually updated)

VanishingPointCameraCalibration

Camera self-calibration using vanishing point method.

ccvs

Camera Calibration for Video Surveillance Toolbox

BEVSee

[CVPR2024] BEVSee

processmining

share automation process mining assets

ClinTrajan

Finding trajectories, bifurcations and quantifying pseudotime in large clinical datasets

RoadUserPathways

Python code for clustering trajectories

Manual-Operations

sequence-alignment-conformance-checking