hufangjian Goto Github PK

paddleocr

Awesome OCR toolkits based on PaddlePaddle （8.6M ultra-lightweight pre-trained model, support training and deployment among server, mobile, embeded and IoT devices）

pdftabextract

A set of tools for extracting tables from PDF files helping to do data mining on (OCR-processed) scanned documents.

photowakeuphmr

HMR modified for PhotoWakeUP input

psenet

keras implementation of PSENET

python-100-days

Python - 100天从新手到大师

pytorch-deep-image-matting

Pytorch implementation of deep image matting

pytorch_semantic_human_matting

This is an unofficial implementation of the paper "Semantic human matting".

rcan

PyTorch code for our ECCV 2018 paper "Image Super-Resolution Using Very Deep Residual Channel Attention Networks"

sa-ssd

segmentation.x

Papers and Benchmarks about semantic segmentation, instance segmentation, panoptic segmentation and video segmentation

semantic-segmentation-suite

Semantic Segmentation Suite in TensorFlow. Implement, train, and test new Semantic Segmentation models easily!

semantic_human_matting

Semantic Human Matting

slowfast

PySlowFast: video understanding codebase from FAIR for reproducing state-of-the-art video models.

smartcamera

📷SmartCamera 是一个 Android 相机拓展库，能够实时采集并且识别相机内物体边框是否吻合指定区域。SmartCamera is an Android camera extension library，provides a scanning module that can recognizes whether the object's border inside the camera matches the area in real time.

smartcropper

🔥 A library for cropping image in a smart way that can identify the border and correct the cropped image. 智能图片裁剪框架。自动识别边框，手动调节选区，使用透视变换裁剪并矫正选区；适用于身份证，名片，文档等照片的裁剪。

stronger-yolo-pytorch

Pytorch implementation of Stronger-Yolo with channel pruning and Mobiledevice deployment.

tengine

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

tensorrt

TensorRT-7 Network Lib 包括常用目标检测、关键点检测、人脸检测、OCR等 可训练自己数据

tnn

TNN：由腾讯优图实验室打造，移动端高性能、轻量级推理框架，同时拥有跨平台、高性能、模型压缩、代码裁剪等众多突出优势。TNN框架在原有Rapidnet、ncnn框架的基础上进一步加强了移动端设备的支持以及性能优化，同时也借鉴了业界主流开源框架高性能和良好拓展性的优点。目前TNN已经在手Q、微视、P图等应用中落地，欢迎大家参与协同共建，促进TNN推理框架进一步完善。

vid2vid

Pytorch implementation of our method for high-resolution (e.g. 2048x1024) photorealistic video-to-video translation.

video-classification

Tutorial for video classification/ action recognition using 3D CNN/ CNN+RNN on UCF101

vividfaces

Vivid faces contains a demo of applying FRCNN on mobile platforms for extracting and training facial landmarks and 3D morph animations. Currently the only working open model of facial feature keypoints extraction on tensorflow.

yolo5_caffe_hisi3559

yolov5: pytorch->onnx->caffe->hisi3559

yolov3

YOLOv3 in PyTorch > ONNX > CoreML > iOS

yolov3-model-pruning

在 oxford hand 数据集上对 YOLOv3 做模型剪枝（network slimming）

yolov5-hisi3559a-train

yolov5训练转onnx转caffe工程 直接可用

zongjie