README.md

# DAN: a Segmentation-free Document Attention Network for Handwritten Document Recognition

[![Python >= 3.10](https://img.shields.io/badge/Python-%3E%3D3.10-blue.svg)](https://www.python.org/downloads/release/python-3100/)

For more details about this package, make sure to see the documentation available at <https://atr.pages.teklia.com/dan/>.

This is an open-source project, licensed using [the MIT license](https://opensource.org/license/mit/).

## Development

For development and tests purpose it may be useful to install the project as a editable package with pip.

This package is based on a GitLab package registry containing all the nerval source code.
You need [a personal access token](https://docs.gitlab.com/ee/user/profile/personal_access_tokens.html) and access to the [nerval repository](https://gitlab.teklia.com/ner/nerval) in order to install this module. You will need to add the below to your `~/.netrc` file:

```shell
machine gitlab.teklia.com
login __token__
password <YOUR_PERSONAL_TOKEN>
```

Then you can install the package as a editable package with pip:

```shell
pip3 install --index-url https://gitlab.teklia.com/api/v4/projects/210/packages/pypi/simple -e .
```

### Linter

Code syntax is analyzed before submitting the code.\
To run the linter tools suite you may use pre-commit.

```shell
pip install pre-commit
pre-commit run -a
```

### Run tests

Tests are executed with `tox` using [pytest](https://pytest.org).
To install `tox`,

```shell
pip install tox
tox
```

To reload the test virtual environment you can use `tox -r`

Run a single test module: `tox -- <test_path>`
Run a single test: `tox -- <test_path>::<test_function>`

The tests use a large file stored via [Git-LFS](https://docs.gitlab.com/ee/topics/git/lfs/). Make sure to run `git-lfs pull` before running them.

### Update documentation

Please keep the documentation updated when modifying or adding features.
It's pretty easy to do:

```shell
pip install -r doc-requirements.txt
mkdocs serve
```

You can then write in Markdown in the relevant `docs/*.md` files, and see live output on <http://localhost:8000>.

## Inference

To apply DAN to an image, one needs to first add a few imports and to load an image. Note that the image should be in RGB.

```python
import cv2
from dan.ocr.predict.inference import DAN

image = cv2.cvtColor(cv2.imread(IMAGE_PATH), cv2.COLOR_BGR2RGB)
```

Then one can initialize and load the trained model with the parameters used during training. The directory passed as parameter should have:

- a `model.pt` file,
- a `charset.pkl` file,
- a `parameters.yml` file corresponding to the `inference_parameters.yml` file generated during training.

```python
model_path = "models"

model = DAN("cpu")
model.load(model_path, mode="eval")
```

To run the inference on a GPU, one can replace `cpu` by the name of the GPU. In the end, one can run the prediction:

```python
text, confidence_scores = model.predict(image, confidences=True)
```

## Training

This package provides three subcommands. To get more information about any subcommand, use the `--help` option.

### Get started

See the [dedicated page](https://atr.pages.teklia.com/dan/get_started/training/) on the official DAN documentation.

### Data extraction from Arkindex

See the [dedicated page](https://atr.pages.teklia.com/dan/usage/datasets/extract/) on the official DAN documentation.

### Model training

See the [dedicated page](https://atr.pages.teklia.com/dan/usage/train/) on the official DAN documentation.

### Model prediction

See the [dedicated page](https://atr.pages.teklia.com/dan/usage/predict/) on the official DAN documentation.