Skip to content
Snippets Groups Projects

Remove add_eot and add_sot parameters from training configuration

Merged Remove add_eot and add_sot parameters from training configuration
remove-add-eot-and-add-sot into main
Merged Manon Blanco requested to merge remove-add-eot-and-add-sot into main
Viewing commit 0a80493b
Prev
Show latest version
1 file
+ 2
− 2
Compare changes
  • Side-by-side
  • Inline
docs/usage/train/parameters.md
+ 2
− 2
@@ -8,7 +8,7 @@ All hyperparameters are specified and editable in the training scripts (meaning
| `dataset_name` | Name of the dataset. | `str` | |
| `dataset_level` | Level of the dataset. Should be named after the element type. | `str` | |
| `dataset_variant` | Variant of the dataset. Usually empty for HTR datasets, `"_sem"` for HTR+NER datasets. | `str` | |
| `dataset_path` | Path to the dataset. | `str` |
| `dataset_path` | Path to the dataset. | `str` | |
| `dataset_params.config.dataset_manager` | Dataset manager class. | custom class | `OCRDatasetManager` |
| `dataset_params.config.dataset_class` | Dataset class. | custom class | `OCRDataset` |
| `dataset_params.config.datasets` | Dataset dictionary with the dataset name as key and dataset path as value. | `dict` | |
@@ -18,7 +18,7 @@ All hyperparameters are specified and editable in the training scripts (meaning
| `dataset_params.config.width_divisor` | Factor to reduce the height of the feature vector before feeding the decoder. | `int` | `32` |
| `dataset_params.config.padding_value` | Image padding value. | `int` | `0` |
| `dataset_params.config.padding_token` | Transcription padding value. | `int` | `None` |
| `dataset_params.config.constraints` | Whether to add end-of-transcription and start-of-transcription tokens in labels. | `list` | `["add_eot", "add_sot"]` |
| `dataset_params.config.constraints` | Whether to add end-of-transcription and start-of-transcription tokens in labels. | `list` | `[]` |
| `dataset_params.config.preprocessings` | List of pre-processing functions to apply to input images. | `list` | (see [dedicated section](#data-preprocessing)) |
| `dataset_params.config.augmentation` | Configuration for data augmentation. | `dict` | (see [dedicated section](#data-augmentation)) |