senlinuc

caffe_ocr

主流ocr算法研究实验性的项目，目前实现了CNN+BLSTM+CTC架构

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。

caffe-intel

This fork of BVLC/Caffe is dedicated to improving performance of this deep learning framework when running on CPU, in particular Intel® Xeon processors (HSW+) and Intel® Xeon Phi processors

DPED

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

Attention-OCR

Visual Attention based OCR

C3D

C3D is a modified version of BVLC caffe to support 3D ConvNets.

caffe-augmentation

Data Augmentation for Caffe

caffe-face

This branch is developed for deep face recognition

CTPN

Detecting Text in Natural Image with Connectionist Text Proposal Network

ethereon-netscope

Hidden-Two-Stream

Caffe implementation for "Hidden Two-Stream Convolutional Networks for Action Recognition"

libfacedetection

A fast binary library for face detection and face landmark detection in images. The face detection speed can reach 1500FPS. You can use it free of charge with any purpose.

places365

The Places365-CNNs for Scene Classification

SENet

Squeeze-and-Excitation Networks

Seq2Seq

Caffe implementation of Seq2Seq model for machine translation

torch_light