基于大模型搭建的聊天机器人，同时支持 企业微信、微信 公众号、飞书、钉钉 等接入，可选择GPT3.5/GPT4.0/Claude/文心一言/讯飞星火/通义千问/Gemini/GLM-4/Claude/LinkAI，能处理文本、语音和图片，访问操作系统和互联网，支持基于自有知识库进行定制企业智能客服。

Grok open release

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

Dense Retrieval and Retrieval-augmented LLMs

Langchain-Chatchat（原Langchain-ChatGLM）基于 Langchain 与 ChatGLM 等语言模型的本地知识库问答 | Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM) QA app with langchain

Grounded-SAM: Marrying Grounding-DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything

A toolkit for making real world machine learning and data analysis applications in C++

YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/

✔（已完结）最全面的 深度学习 笔记【我是土堆 Pytorch】【李沐 动手学深度学习】【吴恩达 深度学习】

深度学习500问，以问答形式对常用的概率知识、线性代数、机器学习、深度学习、计算机视觉等热点问题进行阐述，以帮助自己及有需要的读者。 全书分为18个章节，50余万字。由于水平有限，书中不妥之处恳请广大读者批评指正。 未完待续............ 如有意合作，联系[email protected] 版权所有，违权必究 Tan 2018.06

⚡️An Easy-to-use and Fast Deep Learning Model Deployment Toolkit for ☁️Cloud 📱Mobile and 📹Edge. Including Image, Video, Text and Audio 20+ main stream scenarios and 150+ SOTA models with end-to-end…

Object Detection toolkit based on PaddlePaddle. It supports object detection, instance segmentation, multiple object tracking and real-time multi-person keypoint detection.

A flexible, high-performance carrier for machine learning models（『飞桨』服务化部署框架）

🛠 A lite C++ toolkit of awesome AI models with ONNXRuntime, NCNN, MNN and TNN. YOLOX, YOLOP, MODNet, YOLOR, NanoDet, YOLOX, SCRFD, YOLOX . MNN, NCNN, TNN, ONNXRuntime, CPU/GPU.

PySlowFast: video understanding codebase from FAIR for reproducing state-of-the-art video models.

Implementation of popular deep learning networks with TensorRT network definition API

Real-Time and Accurate Full-Body Multi-Person Pose Estimation&Tracking System

⚡ Based on Yolo's low-power, ultra-lightweight universal target detection algorithm, the parameter is only 250k, and the speed of the smart phone mobile terminal can reach ~300fps+

🔥🔥🔥🔥 YOLO with Transformers and Instance Segmentation, with TensorRT acceleration! 🔥🔥🔥

OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark

Code release for ConvNeXt model

Official implementation of DeepLabCut: Markerless pose estimation of user-defined features with deep learning for all animals incl. humans

这是一个mobilenet-yolov4的库，把yolov4主干网络修改成了mobilenet，修改了Panet的卷积组成，使参数量大幅度缩小。

A curated list of the top 10 computer vision papers in 2021 with video demos, articles, code and paper reference.

代码 -《深度学习之PyTorch物体检测实战》

⚡ Based on yolo's ultra-lightweight universal target detection algorithm, the calculation amount is only 250mflops, the ncnn model size is only 666kb, the Raspberry Pi 3b can run up to 15fps+, and …

Pretrained Pytorch face detection (MTCNN) and facial recognition (InceptionResnet) models

Face recognition using Tensorflow