Official repo for "Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models"

Implementing a ChatGPT-like LLM in PyTorch from scratch, step by step

Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperation

MiniCPM3-4B: An edge-side LLM that surpasses GPT-3.5-Turbo.

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

Pretrain, finetune and deploy AI models on multiple GPUs, TPUs with zero code changes.

大家好，这是cv调包侠开源原创项目，您可以特别方便地通过我的auto-Maker实现目标检测数据集的实时生成，包括：实时数据采集、自动标注、转换、增强，并可以直接进行yolov3、yolov4、yolov5、eficientdet等，它可以直接导出到onnx，通过openvino和tensor-RT加速，除了检测外，还支持分类算法，可以在一分钟内完成图像的智能分类。欢迎来star Hello…

NanoDet-Plus⚡Super fast and lightweight anchor-free object detection model. 🔥Only 980 KB(int8) / 1.8MB (fp16) and run 97FPS on cellphone🔥

Use efficientdet - Python version to realize intelligent retail model training, provide data sets and trained model files ~ welcome star使用Efficientdet -pytorch版实现智能零售模型训练，提供数据集与训练好的模型文件~欢迎star

Game Agent Framework. Helping you create AIs / Bots that learn to play any game you own!

Geometric Computer Vision Library for Spatial AI

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

💃 Real-time single person pose estimation for Android and iOS.

A light and fast one class detection framework for edge devices. We provide face detector, head detector, pedestrian detector, vehicle detector......

[CVPR 2020] VoVNet backbone networks for detectron2

test example of paper, Can WiFi Estimate Person Pose?

Code of paper, Person-in-WiFi: Fine-grained Person Perception using WiFi

A General-purpose Task-parallel Programming System using Modern C++

Object Detection End-to-End framework

A tool using OpenCV to annotate images for image classification, optical character reading, ...

darknet neural network addon for openFrameworks

deploy mobileNet on NCNN

The world's simplest facial recognition api for Python and the command line

face detection alignment recognition reconstruction ...

Windows and Linux version of Darknet Yolo v2 Neural Networks for object detection

a c++ implementation of face alignment in 3000fps

Models and examples built with TensorFlow