Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/xieyufei1993/InceptText-Tensorflow
An Implementation of the alogrithm in paper IncepText: A New Inception-Text Module with Deformable PSROI Pooling for Multi-Oriented Scene Text Detection
https://github.com/xieyufei1993/InceptText-Tensorflow
Last synced: 3 months ago
JSON representation
An Implementation of the alogrithm in paper IncepText: A New Inception-Text Module with Deformable PSROI Pooling for Multi-Oriented Scene Text Detection
- Host: GitHub
- URL: https://github.com/xieyufei1993/InceptText-Tensorflow
- Owner: xieyufei1993
- Created: 2018-09-06T09:41:48.000Z (almost 6 years ago)
- Default Branch: master
- Last Pushed: 2018-11-22T14:31:42.000Z (over 5 years ago)
- Last Synced: 2024-01-16T02:47:42.139Z (5 months ago)
- Language: Python
- Homepage:
- Size: 976 KB
- Stars: 115
- Watchers: 9
- Forks: 31
- Open Issues: 10
-
Metadata Files:
- Readme: README.md
Lists
- awesome-ocr - InceptText-Tensorflow - An Implementation of the alogrithm in paper IncepText: A New Inception-Text Module with Deformable PSROI Pooling for Multi-Oriented Scene Text Detection. (3. <a name='Textdetectionandlocalization'></a>Text detection and localization / 2.1. <a name='OCRGUI'></a>OCR GUI)
- awesome-ocr - InceptText-Tensorflow - An Implementation of the alogrithm in paper IncepText: A New Inception-Text Module with Deformable PSROI Pooling for Multi-Oriented Scene Text Detection. (Text detection and localization / Form Segmentation)
README
# InceptText-Tensorflow
An Implementation of the alogrithm in paper IncepText: A New Inception-Text Module with Deformable PSROI Pooling for Multi-Oriented Scene Text Detection## Introduction
### Tensorflow=1.4.0### Preparation
1.gcc 4.9
2.cuda8.0
3.cd lib && make
- 可能遇到的错误:
1.![error1](error_pic/error1.jpg)
解决办法:把cuda路径添加到系统环境变量,然后改为#include
2.![error2](error_pic/error2.jpg)
解决办法:找到nsync_cv.h的绝对路径然后include
3.![error3](error_pic/error3.jpg)
解决办法:找到nsync_mu.h的绝对路径然后include
## Download
### 1.Models trained on ICDAR 2017
### 2.Resnet V1 50 provided by tensorflow slim[ResNet-v1](http://download.tensorflow.org/models/resnet_v1_50_2016_08_28.tar.gz)## Train
### python train_main.py## Test
### python test.py