MagicSource

tensorflow_poems. 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！

yolov7_d2. 🔥🔥🔥🔥 (Earlier YOLOv7 not official one) YOLO with Transformers and Instance Segmentation, with TensorRT acceleration! 🔥🔥🔥

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

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

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

DCNv2_latest. DCNv2 supports decent pytorch such as torch 1.5+ (now 1.8+)

keras_frcnn. Keras Implementation of faster-rcnn

Crane. 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..

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

tensorflow_novelist. 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！！

AI-Infer-Engine-From-Zero. 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

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

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

Namo-R1. A CPU Realtime VLM in 500M. Surpassed Moondream2 and SmolVLM. Training from scratch with ease.

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

pytorch_chatbot. A Marvelous ChatBot implement using PyTorch.

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

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

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

movenet. Google's Next Gen Pose Estimation in PyTorch

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

Spider12306. 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。

TrafficLightsDetection. using SSD and caffe detect traffic lights on LISA dataset

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

simpleocv. Make a minimal OpenCV runable on any where, WIP

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

yolov3_tf2. Yolov3 implemented with brand new TensorFlow 2.0 API (both train and prediction)

yolov7-face. Next Gen Face detection based on YOLOv7

FruitsNutsSeg. detectron2 support self-define data train

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

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

LLaVA-Magvit2. LLaVA combines with Magvit Image tokenizer, training MLLM without an Vision Encoder. Unifying image understanding and generation.

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

textfrontend. 单独维护的中文TTS

OpenHandMocap. Python

tfboys. TensorFlow and Pytorch practice codes with purity and simplicity.

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

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

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

pt_mobilenetv2_deeplabv3. Fast accurate realtime segmentation with DeepLabV3 and MobileNetV2 backbone

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

Shadowless. A Fast and Open Source Autonomous Perception System.

aural. A Tiny Project For ASR model training and Deployment

wanwu_release. Wanwu models release, code will be released soon

yolovn. Just another yolo variant.

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

spconv. Pytorch layer needed by Second Lidar detector.

pilgrim_torch2trt. Pilgrim Project: torch2trt, quick convert your pytorch model to TensorRT engine.

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

realrender. 3D mesh render without pain.

daybreak_release. Daybreak APP release

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

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

tensorflow_yolov3. A Detailed and Optimized Implementation of Yolo-V3 in Original TensorFlow.

VIBE_yolov5. Using YOLOv5 as detection on VIBE

gofind. gofind - your personal find helper