DataXujing

YOLOv8

:fire: Official YOLOv8模型训练和部署

TensorRT-DETR

:zap::zap::zap:NVIDIA-阿里2021 TRT比赛 `二等奖` 代码提交 团队：美迪康 AI Lab :rocket::rocket::rocket:

ncnn_android_yolov8

QT+NCNN 小米手机运行YOLOv8s

xiaoX

flask+seq2seq【TensorFlow1.0, Pytorch】 :art: :art: 在线聊天机器人 https://mp.weixin.qq.com/s/VpiAmVSTin3ALA8MnzhCJA 或 https://ask.hellobi.com/blog/python_shequ/14486

YOLOv7

:fire::fire::fire: Official YOLOv7训练自己的数据集并实现端到端的TensorRT模型加速推断

YOLOv9

:fire: YOLOv9 paper解析，训练自己的数据集，TensorRT端到端部署， NCNN安卓手机部署

TensorRT-LLM-ChatGLM3

:fire: 大模型部署实战：TensorRT-LLM, Triton Inference Server, vLLM

ASR-paper

:fire: ASR教程: https://dataxujing.github.io/ASR-paper/

ncnn_android_yolov6

ncnn qt yolov6

AIGC-paper

AIGC learning

LLM-virtual-bilibilier

大模型驱动的虚拟主播

ncnn_android_yolov9

YOLOv9 QT+NCNN实现安卓端部署

TTS-paper

🔥 语音合成（TTS）,语音克隆教程: https://dataxujing.github.io/TTS-paper/#/

DataXujing

Mask-RCNN-TensorRT

:bug: TensorRT 实现Mask RCNN推断

django2-ueditor

:fire::fire::fire:Django2中集成xadmin和ueditor

SpotM2-Jetson

:dog: 【NVIDIA Jetson Edge AI开发者大赛】-- 美迪康 AI Lab团队代码提交

AI-Vtuber

AI Vtuber是一个由 【ChatterBot/ChatGPT/claude/langchain（本地/llm）/chatglm/text-generation-webui/闻达/千问/kimi】 驱动的虚拟主播【Live2D/UE/xuniren】，可以在 【Bilibili/抖音/快手/微信视频号/斗鱼/YouTube/twitch/TikTok】 直播中与观众实时互动 或 直接在本地进行聊天。它使用TTS技术【edge-tts/VITS/elevenlabs/bark/bert-vits2/睿声】生成回答并可以选择【so-vits-svc/DDSP-SVC】变声；指令协同SD画图。

awesome-chatgpt

Curated list of awesome tools, demos, docs for ChatGPT and GPT-3

awesome-chinese-ner

中文命名实体识别。包含目前最新的中文命名实体识别论文、中文实体识别相关工具、数据集，以及中文预训练模型、词向量、实体识别综述等。

ColossalAI

Colossal-AI: A Unified Deep Learning System for Big Model Era

EasyCV

An all-in-one toolkit for computer vision

External-Attention-pytorch

🍀 Pytorch implementation of various Attention Mechanisms, MLP, Re-parameter, Convolution, which is helpful to further understand papers.⭐⭐⭐

face_recognition

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

mediapipe

Cross-platform, customizable ML solutions for live and streaming media.

OC_SORT

The official repo for OC-SORT: Observation-Centric SORT on video Multi-Object Tracking. OC-SORT is simple, online and robust to occlusion/non-linear motion.

pycorrector

pycorrector is a toolkit for text error correction. 文本纠错，实现了Kenlm，T5，MacBERT，ChatGLM3，LLaMA等模型应用在纠错场景，开箱即用。

sklearn-porter

Transpile trained scikit-learn estimators to C, Java, JavaScript and others.

tflite2tensorflow

Generate saved_model, tfjs, tf-trt, EdgeTPU, CoreML, quantized tflite, ONNX, OpenVINO, Myriad Inference Engine blob and .pb from .tflite. Support for building environments with Docker. It is possible to directly access the host PC GUI and the camera to verify the operation. NVIDIA GPU (dGPU) support. Intel iHD GPU (iGPU) support. Supports inverse quantization of INT8 quantization model.

vllm

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