Hyper-Table-OCR | designed OCR pipeline for universal boarded table
kandi X-RAY | Hyper-Table-OCR Summary
kandi X-RAY | Hyper-Table-OCR Summary
Hyper-Table-OCR is a C++ library. Hyper-Table-OCR has no bugs, it has no vulnerabilities and it has low support. You can download it from GitHub.
A carefully-designed OCR pipeline for universal boarded table recognition and reconstruction.
A carefully-designed OCR pipeline for universal boarded table recognition and reconstruction.
Support
Quality
Security
License
Reuse
Support
Hyper-Table-OCR has a low active ecosystem.
It has 116 star(s) with 30 fork(s). There are 1 watchers for this library.
It had no major release in the last 6 months.
There are 5 open issues and 8 have been closed. On average issues are closed in 30 days. There are no pull requests.
It has a neutral sentiment in the developer community.
The latest version of Hyper-Table-OCR is current.
Quality
Hyper-Table-OCR has 0 bugs and 0 code smells.
Security
Hyper-Table-OCR has no vulnerabilities reported, and its dependent libraries have no vulnerabilities reported.
Hyper-Table-OCR code analysis shows 0 unresolved vulnerabilities.
There are 0 security hotspots that need review.
License
Hyper-Table-OCR does not have a standard license declared.
Check the repository for any license declaration and review the terms closely.
Without a license, all rights are reserved, and you cannot use the library in your applications.
Reuse
Hyper-Table-OCR releases are not available. You will need to build from source code and install.
Installation instructions, examples and code snippets are available.
It has 23975 lines of code, 447 functions and 100 files.
It has high code complexity. Code complexity directly impacts maintainability of the code.
Top functions reviewed by kandi - BETA
kandi's functional review helps you automatically verify the functionalities of the libraries and avoid rework.
Currently covering the most popular Java, JavaScript and Python libraries. See a Sample of Hyper-Table-OCR
Currently covering the most popular Java, JavaScript and Python libraries. See a Sample of Hyper-Table-OCR
Hyper-Table-OCR Key Features
No Key Features are available at this moment for Hyper-Table-OCR.
Hyper-Table-OCR Examples and Code Snippets
No Code Snippets are available at this moment for Hyper-Table-OCR.
Community Discussions
No Community Discussions are available at this moment for Hyper-Table-OCR.Refer to stack overflow page for discussions.
Community Discussions, Code Snippets contain sources that include Stack Exchange Network
Vulnerabilities
No vulnerabilities reported
Install Hyper-Table-OCR
Download from here: GoogleDrive.
This project is developed and tested on:. An NVIDIA GPU device is compulsory for reasonable inference duration, while GPU with less than 6GB VRAM may experience Out of Memory exception when loading multiple models. You may comment some models in web/__init__.py if experiencing such situation. No version-specific framework feature is used in this project, so this means you could still enjoy it with lower versions of these frameworks. However, at this time(19th Dec, 2020), users with RTX 3000 Series device may have no access to compiled binary of Tensorflow, onnxruntime-gpu, mmdetection, PaddlePaddle via pip or conda. Some building tutorials for Ubuntu are as follows: Tensorflow: https://gist.github.com/kmhofmann/e368a2ebba05f807fa1a90b3bf9a1e03 PaddlePaddle: https://www.paddlepaddle.org.cn/install/quick?docurl=/documentation/docs/zh/2.0-rc1/install/compile/linux-compile.html mmdetection: https://mmdetection.readthedocs.io/en/latest/get_started.html#installation onnxruntime-gpu: https://github.com/microsoft/onnxruntime/blob/master/BUILD.md.
Ubuntu 18.04
RTX 3070 with Driver 455.45.01 & CUDA 11.1 & cuDNN 8.0.4
Python 3.8.3
PyTorch 1.7.0+cu110
Tensorflow 2.5.0
PaddlePaddle 2.0.0-rc1
mmdetection 2.7.0
onnxruntime-gpu 1.6.0
This project is developed and tested on:. An NVIDIA GPU device is compulsory for reasonable inference duration, while GPU with less than 6GB VRAM may experience Out of Memory exception when loading multiple models. You may comment some models in web/__init__.py if experiencing such situation. No version-specific framework feature is used in this project, so this means you could still enjoy it with lower versions of these frameworks. However, at this time(19th Dec, 2020), users with RTX 3000 Series device may have no access to compiled binary of Tensorflow, onnxruntime-gpu, mmdetection, PaddlePaddle via pip or conda. Some building tutorials for Ubuntu are as follows: Tensorflow: https://gist.github.com/kmhofmann/e368a2ebba05f807fa1a90b3bf9a1e03 PaddlePaddle: https://www.paddlepaddle.org.cn/install/quick?docurl=/documentation/docs/zh/2.0-rc1/install/compile/linux-compile.html mmdetection: https://mmdetection.readthedocs.io/en/latest/get_started.html#installation onnxruntime-gpu: https://github.com/microsoft/onnxruntime/blob/master/BUILD.md.
Ubuntu 18.04
RTX 3070 with Driver 455.45.01 & CUDA 11.1 & cuDNN 8.0.4
Python 3.8.3
PyTorch 1.7.0+cu110
Tensorflow 2.5.0
PaddlePaddle 2.0.0-rc1
mmdetection 2.7.0
onnxruntime-gpu 1.6.0
Support
In boardered/extractor.py, we define a TraditionalExtractor based on traditional computer vision techniques and a UNetExtractor based on UNet pixel-level sematic segmentation model. Feel free to derive from the following abstract class:.
Find more information at:
Reuse Trending Solutions
Find, review, and download reusable Libraries, Code Snippets, Cloud APIs from over 650 million Knowledge Items
Find more librariesStay Updated
Subscribe to our newsletter for trending solutions and developer bootcamps
Share this Page
