dawsonia.prepare

NOTE: This used to be the change_format.py script.

Module Contents

Functions

new_label	Encodes a new hyphenated label in the format for Washington dataset
convert	Seperate file ID and generate new_label.
command	Creates new train, validation, test and ground truth text files in “washington” format for the HTR network and copies in image as input data for the model.

Data

app

API

dawsonia.prepare.app

‘Typer(…)’

dawsonia.prepare.new_label(label: str) → str

Encodes a new hyphenated label in the format for Washington dataset

dawsonia.prepare.convert(name: str, word_end_suffix: bool) → tuple[str, str]

Seperate file ID and generate new_label.

dawsonia.prepare.command(n_train: int, n_val: int, n_test: int, label_path: pathlib.Path = Path('/local_disk/', 'data', 'ai-for-obs', 'interim', 'label_old'), model_path: pathlib.Path = Path('/local_disk/', 'data', 'ai-for-obs', 'interim', 'model_tmp'), word_end_suffix: bool = False, source: str = 'washington', config: pathlib.Path = typer.Option('dawsonia.toml', *config_cli_names, **config_kwargs))

Creates new train, validation, test and ground truth text files in “washington” format for the HTR network and copies in image as input data for the model.

Parameters

---

n_train: int Number of images in training set

n_val: int Number of images in validation set

n_test: int Number if images in test set. NOTE: If n_test == -1, all the files from label_path would be used for testing

label_path: Path Path to label directory (where the pictures are located).