MagicSource

中文古诗自动作诗机器人，x炸天，基于tensorflow1.10 api，正在积极维护升级中，快star，保持更新！

🔥🔥🔥🔥 (Earlier YOLOv7 not official one) YOLO with Transformers and Instance Segmentation, with TensorRT acceleration! 🔥🔥🔥

alfred-py: A deep learning utility library for **human**, more detail about the usage of lib to: https://zhuanlan.zhihu.com/p/341446046

🔥🔥 Kokoro in Rust. https://huggingface.co/hexgrad/Kokoro-82M Insanely fast, realtime TTS with high quality you ever have.

Final Weibo Crawler Scrap Anything From Weibo, comments, weibo contents, followers, anything. The Terminator

thor: C++ helper library, for deep learning purpose

DCNv2 supports decent pytorch such as torch 1.5+ (now 1.8+)

Keras Implementation of faster-rcnn

A Pure Rust based LLM, VLM, VLA, TTS, OCR Inference Engine, powering by Candle & Rust. Alternate to your llama.cpp but much more simpler and cleaner..

模仿莎士比亚创作戏剧！屌炸天的是还能创作金庸武侠小说！快star，保持更新！！

关于自建AI推理引擎的手册，从0开始你需要知道的所有事情

Deep fake ready to train on any 2 pair dataset with higher resolution

Update Version of weibo_terminator, This is Workflow Version aim at Get Job Done!

A CPU Realtime VLM in 500M. Surpassed Moondream2 and SmolVLM. Training from scratch with ease.

Neural Network Blocks - Collect all kinds of fancy model blocks for you to build more powerful neural network model.

A Marvelous ChatBot implement using PyTorch.

a implement of LSTM using Keras for time series prediction regression problem

Experiments based on CenterNet (more backbones, TensorRT deployment and mask head)

Accelerated SMPL operation, commonly used in generate 3D human mesh, STAR included.

Google's Next Gen Pose Estimation in PyTorch

Minimal But Practical Image Classifier Pipline Using Pytorch, Finetune on ResNet18, Got 99% Accuracy on Own Small Datasets.

基于Python3的12306抢票爬虫，10个线程开抢，智能过滤凌晨12：00到7：00发车的车次。

using SSD and caffe detect traffic lights on LISA dataset

Train your own data using SSD in a more clear and simple way(not include source code)

Make a minimal OpenCV runable on any where, WIP

Multiple basenet MobileNet v1,v2, ResNet combined with SSD detection method and it's variants such as RFB, FSSD etc.

Yolov3 implemented with brand new TensorFlow 2.0 API (both train and prediction)

Next Gen Face detection based on YOLOv7

detectron2 support self-define data train

An C++ Version of Q-Learning, to Train Robot Play with Flappybird!!

imagetokenizer is a python package, helps you encoder visuals and generate visuals token ids from codebook, supports both image and video.

LLaVA combines with Magvit Image tokenizer, training MLLM without an Vision Encoder. Unifying image understanding and generation.

This repo contains usable code convert cityscapes to coco format (Detectron and maskrcnn-benchmark were all broken)

单独维护的中文TTS

No description.

TensorFlow and Pytorch practice codes with purity and simplicity.

Pure, Simple yet Powerful Image Bound Box Making Tool, already cross platform, welcome star and keep updating.

Rotated Box SSD detection Framework with FPN support, next generation object detection framework

A curated list of transformer learning materials, shared blogs, technical reviews.

Fast accurate realtime segmentation with DeepLabV3 and MobileNetV2 backbone

A Tiny Project For ASR model training and Deployment

A Fast and Open Source Autonomous Perception System.

CycleGAN with Productive Generate APIs. Generate Any Image from Your Transfer Model.

Toolkit to Explore 3D data for 3D object detection, point cloud visualization, bev map gen etc. Using KITTI as dummy data

Rust standalone inference of Namo-500M series models. Extremly tiny, runing VLM on CPU.

Just another yolo variant.

Wanwu models release, code will be released soon

Pytorch layer needed by Second Lidar detector.

Use prompt like a pro, master your agents anywhere, any language, any time. Versioning and Managing your prompt in a single vault.

Next Gen MMD runs on all platforms, Windows, Linux, Mac. Will support exchange between vmd and fbx format.

Add support for quantization int4 for faster inference.

Image Caption, Show and Tell.

A Dead Simple and Modularized Multi-Modal Training and Finetune Framework. Compatible to any LLaVA/Flamingo/QwenVL/MiniGemini etc series models.

libnms.so for object detection, can be use in libtorch or caffe or nccn or onnx or TensorRT

Try add Instance Segmentation upon YoloV5

3D mesh render without pain.

Daybreak APP release

Realtime segmentation with ENet, the fast and accurate segmentation net.

An Edit Version of darknet, and this version you can train and predict on your own datasets! more easily!

Using YOLOv5 as detection on VIBE

C++ and ONNXRuntime based VITS voice synthesis

Various test models in WNNX format. It can view with `pip install wnetron && wnetron`

A NetWork Generate Names, Based On Conditional RNN, Set Condition And Generate Different Names.

A Detailed and Optimized Implementation of Yolo-V3 in Original TensorFlow.

gofind - your personal find helper

State-of-art and Reliable Text-summary and Information Extraction

m editor is a modern, easy to use, fast terminal editor then vim or emacs. written in pure Rust.

企业微信机器人或钉钉机器人定制服务，自动推送arxiv最新paper

Quantization and Fast Inference of MLLMs, such as LLaVA, SparkTTS etc.

Python3.6 Scraper Toolbox, You can almost Scrap Anything in this Repo, Welcome Pull Request

Step Audio Inference can be run without errors

Fusion package with transformation between camera and lidar, IMU etc. Autonomous and robot helper.

mxnet训练自己的数据集分类，支持模型断点训练和预测单张图片

NumPy library in Go.

Upload load images(files) to cloud, generate permanent link.

PoseAI LiveLink Compatible on macOS

Visual Odometry Using Mono Camera

TensorFlow implementation of Google Tacotron. Train on Audio and Generate Speech using Text. Which can be Called TTS.

No description.

Realtime Openpose with MobileNetV2 backend

Realtime Point Cloud Segmentation

A Simple Implementation of Neural Style Transfer using Pytorch. You can generate your own art pictures now!

Collection of efficient transformers.

Light weighted replacement of original thor C++ library. More simpler, more clean, more light.

Exploration on Micro Transformers, Unleash the power of mini-transformers!

person tracking in ros

No description.

A Tensorfow Version of the state-of-art Wasserstein GAN, image super resolution, black image colorful, more function are applying...just star!

Caffe tutorial for train own data and predict using python

Simple and over-through process for Tensorflow classify images, using own dataset

Common used component in AI applications. (inference interface, processing utils, serving etc)

Make RSS great again.

Pure C++ Tool Convert Any Multiple ONNX/MNN/pth models into one single file .modelforge.

ONNXRuntime ASR C++

Visualizer for neural network, deep learning, and machine learning models

Library to lean big models combined with Text and Image. And then Diffusion!

This is a Caffe hands on tutorial.

No description.

OpenCV Plugin for UE 5.1, it was supported up to opencv 4.6.0 version. Providing ability call OpenCV inside UE.

Pure C++ Kaldi IO.

Towards 3D real world detection.

Instance Segmentation with discriminate loss

Picbed utils for many open APIs

Tensorflow lstm tutorial, we using lstm generate a novel!

A Clear SSD Implementation in Keras and TensorFlow with Training and Predict.

an Android app for deeplearning

No description.

llama-cpp-python forked version while contains some modifications, provides much more simpler inference API and demo. Integrated with my ChatBots.

Using Mediapipe as a static lib and using in CMake!

DeepMimic support tensorflow 2.8

Official tutorial for beginers in TensorFlow 2.3 with keras, Only 10 minutes become ML master! 10分钟上手TensorFlow成为机器学习大神！

Model compression related, Pruning and quantization

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

DeDacker: Detection Data Checker. A Tool For Checking your Label Bouding Boxes.

ReinforcementLearning Solution About Gym Games, And More Problem that Could Solve By Reinforcement Learning.

xa is your next fastest ai coding agent cli, with RTK built-in, make your token usage minimal by default, supports BYOK and using your own endpoint!

Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

Ruben is a benchmark framework, test on different tasks speed compare with C++, such asa GEMM, CV etc. Mostly for learning purpose.

[CVPR 2022] PoseTriplet: Co-evolving 3D Human Pose Estimation, Imitation, and Hallucination under Self-supervision (Oral)

High-Level Training, Data Augmentation, and Utilities for Pytorch

哔哩哔哩 bilibili 网站后台工程 源码 fork from https://github.com/openbilibili/go-common

支持更多中文大模型的langchain助手

Using Prompt make LLaMA act like Sydeney

contains public images for image bed usage.

: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

A Strong and Easy-to-use Single View 3D Hand+Body Pose Estimator

No description.

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

financial analysis with python

一个新闻阅读安卓端的app

An mxnet implemention of char based sentence generator

Tencent Autolab Sloth Label Tool.

Messengers Demo of Matrix. It's a Product of ChatBot.

C++ Interface of MXNet, Building Inference Network in Snap Time

OpenGL Viewer (OBJ PMD PMX)

LightNet: Light-weight Networks for Semantic Image Segmentation (Cityscapes and Mapillary Vistas Dataset)

Simplify your onnx model

Baishuo gitalk comments container.

Low-cost Inference Package for Big Pretrained Language Models (PLMs)

Calendar widget for flutter that is swipeable horizontally. This widget can help you build your own calendar widget highly customizable.

Open source reverse-engineered clone of DeepNude

PPL Quantization Tool (PPQ) is a powerful offline neural network quantization tool.

Fork of detectron2

A Flutter package that makes it easy to customize and work with your Flutter desktop app window.

Infer LLM in One C++

No description.

ncnn is a high-performance neural network inference framework optimized for the mobile platform

Out-of-box neovim config

MICA - Towards Metrical Reconstruction of Human Faces (ECCV 2022)

test ASR

Template for a simple resume or curriculum vitae (CV), in XeLaTeX.

No description.

my c++ project demo repo

Drop and Drag Upload Your Image to Cloud Pernentely

ouman official website

New version of Smart ChatBot based on tensorflow, this is the 4th generation, more intelligent and more human-like!!!!

The first wechatapp of our company.

Native port of Open Food Facts on Android

No description.

Show and Tell, You'll See..

No description.

No description.

Omini action tokenizer with RVQ, enabling any embodiment action encoding into discrete tokens.

A powerful and modular stable diffusion GUI with a graph/nodes interface.

The official PyTorch implementation of Towards Fast, Accurate and Stable 3D Dense Face Alignment, ECCV 2020.

Chumpy for Python1.12, 1.13, 1.14, newest, maintained, support PR version, if you have any pip install chumpy issue try this version pip install chumpy2

Customized Image2Dataset tool called `mllmdata`, easy convert parquet urls to local dataset fast.

live link face helper

No description.

No description.

Use this plugin to generate waveforms while recording audio in any file formats supported by given encoders or from audio files. We can use gestures to scroll through the waveforms or seek to any position while playing audio and also style waveforms

AG2 (formerly AutoGen): The Open-Source AgentOS. Join us at: https://discord.gg/pAbnFJrkgZ

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

使用Github Action将国外的Docker镜像转存到阿里云私有仓库，供国内服务器使用，免费易用

No description.

My website

free

A series of large language models trained from scratch by developers @01-ai

No description.

No description.

No description.

📒 Self hosted note taking app stored on S3

Enable everyone to develop, optimize and deploy AI models natively on everyone's devices.

Running LLaMA models with int4 quantization in python with llama.cpp

Mono API for nn model inference in Rust, customizable backend

No description.

OSC streaming in C++

No description.

Doing compute on Rust.

No description.

No description.

Easy-to-use Speech Toolkit including SOTA/Streaming ASR with punctuation, influential TTS with text frontend, Speaker Verification System, End-to-End Speech Translation and Keyword Spotting. Won NAACL2022 Best Demo Award.

Transformer related optimization, including BERT, GPT

Visualize your 3d keypoints in a more fancy way

SOTA 3D pose estimation

Code release for "Omni3D A Large Benchmark and Model for 3D Object Detection in the Wild"

An Intelligent Assistant in pure rust.

Tiny, no-nonsense, self-contained, Tensorflow and ONNX inference

No description.

Documents of Yolov7