mrkolarik

OneInchEye

A One Inch CMOS sensor (IMX283) camera board designed for Raspberry Pi

llm-course

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

Datasets

The consolidated datasets available elsewhere

MedNeXt

[MICCAI 2023] MedNeXt is a fully ConvNeXt architecture for 3D medical image segmentation.

instructor

structured outputs for llms

granite-tsfm

Foundation Models for Time Series

D-id_Streaming_Chatgpt

OpenDevin

🐚 OpenDevin: Code Less, Make More

devika

Devika is an Agentic AI Software Engineer that can understand high-level human instructions, break them down into steps, research relevant information, and write code to achieve the given objective. Devika aims to be a competitive open-source alternative to Devin by Cognition AI.

LLaVA

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

lilygo-twatch-sleepdevice

Converts a LilyGo T-Watch 2020 V3 into a sleep therapy device for positional obstructive sleep apnea (POSA) and snoring

mistral-inference

Official inference library for Mistral models

vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

ImageAI

A python library built to empower developers to build applications and systems with self-contained Computer Vision capabilities

DeepStack

The World's Leading Cross Platform AI Engine for Edge Devices

system-design-101

Explain complex systems using visuals and simple terms. Help you prepare for system design interviews.

motioneye

A web frontend for the motion daemon.

motioneyeos

A Video Surveillance OS For Single-board Computers

motioneye-client

Client library for motionEye

LLaMA2-Accessory

An Open-source Toolkit for LLM Development

inference

A fast, easy-to-use, production-ready inference server for computer vision supporting deployment of many popular model architectures and fine-tuned models.

FastestDet

:zap: A newly designed ultra lightweight anchor free target detection algorithm， weight only 250K parameters， reduces the time consumption by 10% compared with yolo-fastest, and the post-processing is simpler

peft

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

awesome-iot

Awesome IoT. A collaborative list of great resources about IoT Framework, Library, OS, Platform

recognize-anything

Open-source and strong foundation image recognition models.

GenerativeModels

MONAI Generative Models makes it easy to train, evaluate, and deploy generative models and related applications

LAVIS

LAVIS - A One-stop Library for Language-Vision Intelligence

CoCa-pytorch

Implementation of CoCa, Contrastive Captioners are Image-Text Foundation Models, in Pytorch

Segment-Any-Anomaly

Official implementation of "Segment Any Anomaly without Training via Hybrid Prompt Regularization (SAA+)".

WinClip

[CVPR 2023] Unofficial re-implementation of "WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentation".