Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/alleveenstra/attentionocr
Attention OCR in Tensorflow 2.0
https://github.com/alleveenstra/attentionocr
computer-vision machine-learning ocr python3 tensorflow2
Last synced: 3 months ago
JSON representation
Attention OCR in Tensorflow 2.0
- Host: GitHub
- URL: https://github.com/alleveenstra/attentionocr
- Owner: alleveenstra
- License: mit
- Created: 2019-11-01T18:04:18.000Z (about 5 years ago)
- Default Branch: master
- Last Pushed: 2023-03-25T00:31:08.000Z (almost 2 years ago)
- Last Synced: 2024-08-01T03:17:02.751Z (6 months ago)
- Topics: computer-vision, machine-learning, ocr, python3, tensorflow2
- Language: Python
- Homepage:
- Size: 101 KB
- Stars: 46
- Watchers: 10
- Forks: 11
- Open Issues: 6
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
- awesome-tensorflow-2 - Attention OCR in Tensorflow 2.0
README
# Attention OCR
A clear and maintainable implementation of Attention OCR in Tensorflow 2.0.
This sequence to sequence OCR model aims to provide a clear and maintainable implementation of attention based OCR.
Please note that this is currently a work in progress.
Documentation is missing, but will be added when the code is stable.
This repository depends upon the following:
* Tensorflow 2.0
* Python 3.6+
## Training a model
To train a model, first download the sources for generating synthetic data:
```bash
cd synthetic
./download_data_sources.sh
```
Next, in this project's root folder, run the training script:
```bash
python3 run.py
```
This will run a test training run.
If everything went well, you'll find a file named "trained.h5" in your directory.
To train a real model you should change the training parameters.
See run.py its arguments to find out what is configurable.
```bash
python3 run.py --help
```
## References
This work is based on the following work:
* [Attention Is All You Need](https://arxiv.org/abs/1706.03762)
## To do
* Make image height variable
* Name all input and output tensors
* Write unit tests with full coverage
* Show a test case on google colab
* Perform a grid search on best parameters for a toy dataset
* Document the whole API
[](https://www.codacy.com/manual/alle.veenstra/attentionocr?utm_source=github.com&utm_medium=referral&utm_content=alleveenstra/attentionocr&utm_campaign=Badge_Grade)