rkshuai Goto Github PK

ocr_detection_ic15

OCR detection for ICDAR2015, which is based on FOTS, the precision is 80.6%.

ocrinaction

onnx

Open Neural Network Exchange

onnx-tensorrt

ONNX-TensorRT: TensorRT backend for ONNX

openpose

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

pcn

Progressive Calibration Networks (PCN) is an accurate rotation-invariant face detector running at real-time speed on CPU, published in CVPR 2018.

pelee

Pelee: A Real-Time Object Detection System on Mobile Devices

pixel_link

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

pmtd

Pyramid Mask Text Detector designed by SenseTime Video Intelligence Research team.

pose-hg-demo

Code to test and use the model from "Stacked Hourglass Networks for Human Pose Estimation"

pose-hg-train

Training and experimentation code used for "Stacked Hourglass Networks for Human Pose Estimation"

pose-residual-network

Code for 'MultiPoseNet: Fast Multi-Person Pose Estimation using Pose Residual Network' paper

progressive_growing_of_gans

Progressive Growing of GANs for Improved Quality, Stability, and Variation

psenet

psenet-todo

Realization of PSENet with pytorch

psenet_tf

publaynet

pwc

Papers with code. Sorted by stars. Updated weekly.

pybind11_opencv_numpy

Implementation of cv::Mat conversion to numpy.array for pybind11

python-rlsa

RUN LENGTH SMOOTHING ALGORITHM(RLSA) is a method mainly used for block segmentation and text discrimination. It helps to extract the necessary block from the document image.

pytorch-caffe-darknet-convert

convert between pytorch, caffe prototxt/weights and darknet cfg/weights

pytorch-pruning

PyTorch Implementation of [1611.06440] Pruning Convolutional Neural Networks for Resource Efficient Inference

pytorchconverter

Pytorch model to caffe & ncnn

qaida

Large scale font independent printed Urdu text data set

r2cnn_faster-rcnn_tensorflow

Rotational region detection based on Faster-RCNN.

r2cnn_fpn_tensorflow

R2CNN: Rotational Region CNN Based on FPN (Tensorflow)

refinedet

Single-Shot Refinement Neural Network for Object Detection

reid-mgn

Reproduction of paper: Learning Discriminative Features with Multiple Granularities for Person Re-Identification

research-charnet

CharNet: Convolutional Character Networks

scanssd

Scanning Single Shot Detector for Math in Document Images