alannewimage Goto Github PK

models

Models and examples built with TensorFlow

moran_v2

MORAN: A Multi-Object Rectified Attention Network for Scene Text Recognition

mvision

机器人视觉 无人驾驶 视觉SLAM ORB LSD SVO DSO 深度学习目标检测yolov3 行为检测 opencv PCL 双目视觉

ncnn

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

ncnnforandroid_objectiondetection_mobilenetssd

利用Mobilenetssd目标检测框架,ncnn前向推理,android项目

onnx

Open Neural Network Exchange

opencv-east

use the opencv interface to run east

openface

Face recognition with deep neural networks.

openpose

OpenPose: Real-time multi-person keypoint detection library for body, face, and hands estimation

pixel_link

Implementation of our paper 'PixelLink: Detecting Scene Text via Instance Segmentation' in AAAI2018

pspnet

Pyramid Scene Parsing Network, CVPR2017.

pytorch

Tensors and Dynamic neural networks in Python with strong GPU acceleration

scenereco

ctpn+crnn Scene character recognition

see

Code for the AAAI 2018 publication "SEE: Towards Semi-Supervised End-to-End Scene Text Recognition"

seetaface2_demo

seetaface第二版sdk包相关测试范例工程

seetafaceengine

seetafaceengine2

selftest

Only for test

tengine

Tengine is a lite, high performance, modular inference engine for embedded device

tensorflow_psenet

This is a tensorflow re-implementation of PSENet: Shape Robust Text Detection with Progressive Scale Expansion Network.My blog:

tesseract

Tesseract Open Source OCR Engine (main repository)

text-detection-ctpn

text detection mainly based on ctpn model in tensorflow, id card detect, connectionist text proposal network

usb_cam

A ROS Driver for V4L USB Cameras

videocapture

:camera:V4L2+OpenCV3.1以MPJG格式采集图像

wassersteingan

wincnn

Winograd minimal convolution algorithm generator for convolutional neural networks.

yolox

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

zphotoengine

Image-process-libraries-like-photoshop

zqcnn

一款比mini-caffe更快的Forward库，觉得好用请点星啊，400星公布快速人脸检测模型，500星公布106点landmark，600星公布人头检测模型，700星公布人脸检测套餐（六种pnet,两种rnet随意混合使用满足各种速度/精度要求）