xiaodongdreams

FastImageProcessing

Fast Image Processing with Fully-Convolutional Networks

CRNN_Attention_OCR_Chinese

CRNN with attention to do OCR,add Chinese recognition

tensorflow-grad-cam

Tensorflow Slim Grad-Cam to Explain Neural Network Predictions with Heatmap or Shading

dfn

focal-loss-1

Focal loss for Dense Object Detection

Multi-View-Networks-for-Text-Classification

Multi-View Deep Neural Networks for Text Classification

Linear-RNN

Keras implementation of LRNN based on Liusifei's work - "Learning Recursive Filters for Low-Level Vision via a Hybrid Neural Network"

ML-in-Action-Code-and-Note

:chart_with_upwards_trend:Machine Learning code in Python3.x. （机器学习实战 py3代码整理）Some notes about the practices:（for reference only）

YOLO_tensorflow

tensorflow implementation of 'YOLO : Real-Time Object Detection'

Arxiv

retrieval-2017-cam

Class-Weighted Convolutional Features for Image Retrieval

Activation-Visualization-Histogram

Compare SELUs (scaled exponential linear units) with other activations on MNIST, CIFAR10, etc.

Chinese_OCR_synthetic_data

The progress was used to generate synthetic dataset for Chinese OCR.

DPED

Software and pre-trained models for automatic photo quality enhancement using Deep Convolutional Networks

hdrnet

An implementation of 'Deep Bilateral Learning for Real-Time Image Enhancement', SIGGRAPH 2017

darknet_mobilenet

mobilenet 与darknet yolo

yolo-qt

focal_loss_pytorch

A PyTorch Implementation of Focal Loss.

darknet-mobilenet

mobilenet model in darknet framework , MobilenetYOLO, compress mobilenet

keras-cam

Keras implementation of class activation mapping

basicOCR

BasicOCR是一个致力于解决自然场景文字识别算法研究的项目。该项目由长城数字大数据应用技术研究院佟派AI团队发起和维护。

residual-attention-network-1

Residual Attention Network for Image Classification

machine-learning-summary

My own study summary,including machine learning knowledge with codes.

SmokeSegmentation

Project on smoke detection from CS231a (Spring 2017)

cabbird

A set of algorithms written in python.

visualizing_cnns

Using Keras and cats to visualize layers from CNNs

torch-Attention-OCR

bionics

仿生学算法实现

datanmachlearn

fastviz

Fast filtering and animation of large dynamic networks