DayBreak-u

chineseocr_lite

超轻量级中文ocr，支持竖排文字识别, 支持ncnn、mnn、tnn推理 ( dbnet(1.8M) + crnn(2.5M) + anglenet(378KB)) 总模型仅4.7M

yolo-face-with-landmark

yoloface大礼包 使用pytroch实现的基于yolov3的轻量级人脸检测（包含关键点）

Thundernet_Pytorch

Implementation Thundernet

darknet_face_with_landmark

加入关键点的darknet训练框架，轻量级的人脸检测，支持ncnn推理

SOLOV2_ncnn

the C++ version of solov2 with ncnn

centernet_mobilenetv2_ncnn

centernet_mobilenetv2 inference by ncnn

thundernet_mmdetection

thundernet ncnn

RefinedetLite.pytorch

Implementation RefinedetLite

seq2seq_ncnn

the C++ version of Seq2Seq with ncnn

Transformer_ncnn

the C++ version of Transformer with ncnn

Snet

train Snet(by thundernet) in imagenet

thundernet_ncnn

the C++ version of thundernet with ncnn

Video_QA

Video Question Answering

CenterNet

Object detection, 3D detection, and pose estimation using center point detection:

-vqa-

file2hive

csv or xls input into hive

mtcnn-pytorch

A face detection algorithm

ouyanghuiyu.github.io

it's my personal website

SOLOv2

SOLOv2: Dynamic, Faster and Stronger, achives 39.5mAP on coco test-dev (36 epochs result)

srmd-ncnn-vulkan

SRMD super resolution implemented with ncnn library

HRNet-Semantic-Segmentation

The OCR approach is rephrased as Segmentation Transformer: https://arxiv.org/abs/1909.11065. This is an official implementation of semantic segmentation for HRNet. https://arxiv.org/abs/1908.07919

ncnn_paddleocr

Android paddleocr demo infer by ncnn