e5e3dca7fbcfbf69132cab8082705099891edc1c to 2769fe6d958a0c385676529489d724c30c482fbb · Automatic Text Recognition / DAN

configs/eval.json

+4 −4

Original line number	Diff line number	Diff line
		@@ -9,9 +9,9 @@
		["training", "train"]
		]
		},
		"val": {
		"training-val": [
		["training", "val"]
		"dev": {
		"training-dev": [
		["training", "dev"]
		]
		},
		"test": {
		@@ -84,7 +84,7 @@
		"validation": {
		"eval_on_valid": true,
		"eval_on_valid_interval": 2,
		"set_name_focus_metric": "training-val",
		"set_name_focus_metric": "training-dev",
		"font": "fonts/LinuxLibertine.ttf",
		"maximum_font_size": 32,
		"nb_logged_images": 5

configs/quickstart.json

+4 −4

Original line number	Diff line number	Diff line
		@@ -19,9 +19,9 @@
		["$dataset_name", "train"]
		]
		},
		"val": {
		"$dataset_name-val": [
		["$dataset_name", "val"]
		"dev": {
		"$dataset_name-dev": [
		["$dataset_name", "dev"]
		]
		},
		"test": {
		@@ -96,7 +96,7 @@
		"eval_on_valid": true,
		"eval_on_valid_interval": 5,
		"eval_on_valid_start": 0,
		"set_name_focus_metric": "$dataset_name-val",
		"set_name_focus_metric": "$dataset_name-dev",
		"font": "fonts/LinuxLibertine.ttf",
		"maximum_font_size": 32,
		"nb_logged_images": 5,

configs/tests.json

+4 −4

Original line number	Diff line number	Diff line
		@@ -9,9 +9,9 @@
		["training", "train"]
		]
		},
		"val": {
		"training-val": [
		["training", "val"]
		"dev": {
		"training-dev": [
		["training", "dev"]
		]
		},
		"test": {
		@@ -85,7 +85,7 @@
		"eval_on_valid": true,
		"eval_on_valid_interval": 2,
		"eval_on_valid_start": 0,
		"set_name_focus_metric": "training-val",
		"set_name_focus_metric": "training-dev",
		"font": "fonts/LinuxLibertine.ttf",
		"maximum_font_size": 32,
		"nb_logged_images": 1

dan/init.py

+1 −1

Original line number	Diff line number	Diff line
		@@ -10,6 +10,6 @@ logging.basicConfig(
		)

		TRAIN_NAME = "train"
		VAL_NAME = "val"
		VAL_NAME = "dev"
		TEST_NAME = "test"
		SPLIT_NAMES = [TRAIN_NAME, VAL_NAME, TEST_NAME]

dan/ocr/mlflow.py

+2 −2

Original line number	Diff line number	Diff line
		@@ -83,7 +83,7 @@ def logging_metrics(
		Log dictionary metrics in the Metrics section of MLflow

		:param display_values: dict, the dictionary containing the metrics to publish on MLflow
		:param step: str, the step for which the metrics are to be published on Metrics section (ex: train, val, test). This will allow a better display on MLflow.
		:param step: str, the step for which the metrics are to be published on Metrics section (ex: train, dev, test). This will allow a better display on MLflow.
		:param epoch: int, the current epoch.
		:param mlflow_logging: bool, allows you to verify that you have the authorization to log on MLflow, defaults to False
		:param is_master: bool, makes sure you're on the right thread, defaults to False
		@@ -107,7 +107,7 @@ def logging_tags_metrics(
		Log dictionary metrics in the Tags section of MLflow

		:param display_values: dict, the dictionary containing the metrics to publish on MLflow
		:param step: str, the step for which the metrics are to be published on Tags section (ex: train, val, test). This will allow a better display on MLflow.
		:param step: str, the step for which the metrics are to be published on Tags section (ex: train, dev, test). This will allow a better display on MLflow.
		:param mlflow_logging: bool, allows you to verify that you have the authorization to log on MLflow, defaults to False
		:param is_master: bool, makes sure you're on the right thread, defaults to False
		"""

docs/get_started/training.md

+2 −2

Original line number	Diff line number	Diff line
		@@ -6,7 +6,7 @@ There are a several steps to follow when training a DAN model.

		To extract the data, DAN uses an Arkindex export database in SQLite format. You will need to:

		1. Structure the data into splits (`train` / `val` / `test`) in a project dataset in [Arkindex](https://demo.arkindex.org/).
		1. Structure the data into splits (`train` / `dev` / `test`) in a project dataset in [Arkindex](https://demo.arkindex.org/).
		1. [Export the project](https://doc.arkindex.org/howto/export/) in SQLite format.
		1. Extract the data with the [extract command](../usage/datasets/extract.md).
		1. Download images with the [download command](../usage/datasets/download.md).
		@@ -22,7 +22,7 @@ output/
		├── labels.json
		├── images
		│ ├── train
		│ ├── val
		│ ├── dev
		│ └── test
		└── language_model
		├── corpus_characters.txt

docs/usage/datasets/download.md

+1 −1

Original line number	Diff line number	Diff line
		@@ -38,7 +38,7 @@ The `--output` directory should have a `split.json` JSON-formatted file with a s
		"text": "ⓢCoufet ⓕBouis ⓑ07.12.14"
		},
		},
		"val": {},
		"dev": {},
		"test": {}
		}
		```

docs/usage/datasets/language_model.md

+1 −1

Original line number	Diff line number	Diff line
		@@ -25,7 +25,7 @@ These files can be generated by the `teklia-dan dataset download` command. More
		"train": {
		"<image_path>": "\u24e2Coufet \u24d5Bouis \u24d107.12.14"
		},
		"val": {},
		"dev": {},
		"test": {}
		}
		```

docs/usage/evaluate/index.md

+4 −4

Original line number	Diff line number	Diff line
		@@ -25,7 +25,7 @@ This will, for each evaluated split:
		\| `--config` \| Path to the configuration file. \| `pathlib.Path` \| \|
		\| `--nerval-threshold` \| Distance threshold for the match between gold and predicted entity during Nerval evaluation. `0` would impose perfect matches, `1` would allow completely different strings to be considered as a match. \| `float` \| `0.3` \|
		\| `--output-json` \| Where to save evaluation results in JSON format. \| `pathlib.Path` \| `None` \|
		\| `--sets` \| Sets to evaluate. Defaults to `train`, `val`, `test`. \| `list[str]` \| `["train", "val", "test"]` \|
		\| `--sets` \| Sets to evaluate. Defaults to `train`, `dev`, `test`. \| `list[str]` \| `["train", "dev", "test"]` \|

		## Examples

		@@ -37,7 +37,7 @@ This will, for each evaluated split:
		\| Split \| CER (HTR-NER) \| CER (HTR) \| WER (HTR-NER) \| WER (HTR) \| WER (HTR no punct) \|
		\| :---: \| :-----------: \| :-------: \| :-----------: \| :-------: \| :----------------: \|
		\| train \| x \| x \| x \| x \| x \|
		\| val \| x \| x \| x \| x \| x \|
		\| dev \| x \| x \| x \| x \| x \|
		\| test \| x \| x \| x \| x \| x \|

		#### 5 worst prediction(s)
		@@ -57,7 +57,7 @@ This will, for each evaluated split:
		\| Split \| CER (HTR-NER) \| CER (HTR) \| WER (HTR-NER) \| WER (HTR) \| WER (HTR no punct) \| NER \|
		\| :---: \| :-----------: \| :-------: \| :-----------: \| :-------: \| :----------------: \| :-: \|
		\| train \| x \| x \| x \| x \| x \| x \|
		\| val \| x \| x \| x \| x \| x \| x \|
		\| dev \| x \| x \| x \| x \| x \| x \|
		\| test \| x \| x \| x \| x \| x \| x \|

		#### Nerval evaluation
		@@ -69,7 +69,7 @@ This will, for each evaluated split:
		\| Surname \| x \| x \| x \| x \| x \| x \|
		\| All \| x \| x \| x \| x \| x \| x \|

		##### val
		##### dev

		\| tag \| predicted \| matched \| Precision \| Recall \| F1 \| Support \|
		\| :-----: \| :-------: \| :-----: \| :-------: \| :----: \| :-: \| :-----: \|

docs/usage/train/tensorboard.md

+6 −6

Original line number	Diff line number	Diff line
		@@ -39,12 +39,12 @@ Alternatively, you can find them in the `Time series` tab.

		The same metrics are computed on the validation set, except for the loss function:

		- `val/{dataset}-val_cer`: the CER.
		- `val/{dataset}-val_cer_no_token`: the CER ignoring punctuation marks.
		- `val/{dataset}-val_ner`: the CER ignoring characters (only NE tokens are considered).
		- `val/{dataset}-val_wer`. the WER.
		- `val/{dataset}-val_wer_no_punct`: the WER ignoring punctuation marks.
		- `val/{dataset}-val_wer_no_token`: the WER ignoring Named Entity (NE) tokens (only characters are considered).
		- `dev/{dataset}-dev_cer`: the CER.
		- `dev/{dataset}-dev_cer_no_token`: the CER ignoring punctuation marks.
		- `dev/{dataset}-dev_ner`: the CER ignoring characters (only NE tokens are considered).
		- `dev/{dataset}-dev_wer`. the WER.
		- `dev/{dataset}-dev_wer_no_punct`: the WER ignoring punctuation marks.
		- `dev/{dataset}-dev_wer_no_token`: the WER ignoring Named Entity (NE) tokens (only characters are considered).

		These metrics can be visualized in the `Scalars` tab in Tensorboard, under the `valid` section.
		<img src="../../../assets/tensorboard/example_scalars_val.png" />

tests/data/analyze/stats.md

+1 −1

Original line number	Diff line number	Diff line
		@@ -55,7 +55,7 @@ Statistics
		\| Median \| 0.0 \| 0.0 \| 0.0 \|
		\| Total \| 0 \| 0 \| 0 \|

		# Val
		# Dev

		## Images statistics

tests/data/evaluate/inference.json

+1 −1

Original line number	Diff line number	Diff line
		@@ -15,7 +15,7 @@
		0.4286
		]
		],
		"val": [
		"dev": [
		[
		"2c242f5c-e979-43c4-b6f2-a6d4815b651d.png",
		"\u24c8A \u24bbCharles \u24b711 \u24c1P \u24b8C \u24c0F \u24c4A \u24c514331",

tests/data/evaluate/metrics_table.md

+2 −2

Original line number	Diff line number	Diff line
		@@ -3,7 +3,7 @@
		\| Split \| CER (HTR-NER) \| CER (HTR) \| WER (HTR-NER) \| WER (HTR) \| WER (HTR no punct) \| NER \|
		\|:-----:\|:-------------:\|:---------:\|:-------------:\|:---------:\|:------------------:\|:----:\|
		\| train \| 18.89 \| 21.05 \| 26.67 \| 26.67 \| 26.67 \| 7.14 \|
		\| val \| 8.82 \| 11.54 \| 50.0 \| 50.0 \| 50.0 \| 0.0 \|
		\| dev \| 8.82 \| 11.54 \| 50.0 \| 50.0 \| 50.0 \| 0.0 \|
		\| test \| 2.78 \| 3.33 \| 14.29 \| 14.29 \| 14.29 \| 0.0 \|

		#### Nerval evaluation
		@@ -22,7 +22,7 @@
		\| Surname \| 2 \| 2 \| 100.0 \| 100.0 \| 100.0 \| 2 \|
		\| ALL \| 15 \| 12 \| 80.0 \| 85.71 \| 82.76 \| 14 \|

		##### val
		##### dev

		\| tag \| predicted \| matched \| Precision \| Recall \| F1 \| Support \|
		\|:----------\|----------:\|--------:\|----------:\|-------:\|------:\|--------:\|

tests/data/extraction/elements/val-page_1-line_1.json→tests/data/extraction/elements/dev-page_1-line_1.json

+0 −0

File moved.

tests/data/extraction/elements/val-page_1-line_2.json→tests/data/extraction/elements/dev-page_1-line_2.json

+0 −0

File moved.

tests/data/extraction/elements/val-page_1-line_3.json→tests/data/extraction/elements/dev-page_1-line_3.json

+0 −0

File moved.

tests/data/extraction/elements/val-page_1.json→tests/data/extraction/elements/dev-page_1.json

+3 −3

Original line number	Diff line number	Diff line
		@@ -8,8 +8,8 @@
		[0, 0]
		],
		"children": [
		"val-page_1-line_1",
		"val-page_1-line_2",
		"val-page_1-line_3"
		"dev-page_1-line_1",
		"dev-page_1-line_2",
		"dev-page_1-line_3"
		]
		}

tests/data/extraction/elements/val.json→tests/data/extraction/elements/dev.json

+1 −1

Original line number	Diff line number	Diff line
		{
		"type": "folder",
		"children": [
		"val-page_1"
		"dev-page_1"
		]
		}

tests/data/extraction/elements/root.json

+1 −1

Original line number	Diff line number	Diff line
		@@ -2,7 +2,7 @@
		"type": "folder",
		"children": [
		"train",
		"val",
		"dev",
		"test"
		]
		}

tests/data/extraction/images/val-page_1-line_1.jpg→tests/data/extraction/images/dev-page_1-line_1.jpg

(30.7 KiB)

File moved.

View file

tests/data/extraction/images/val-page_1-line_2.jpg→tests/data/extraction/images/dev-page_1-line_2.jpg

(31.5 KiB)

File moved.

View file

tests/data/extraction/images/val-page_1-line_3.jpg→tests/data/extraction/images/dev-page_1-line_3.jpg

(30.6 KiB)

File moved.

View file

tests/data/extraction/split.json

+7 −7

Original line number	Diff line number	Diff line
		@@ -380,11 +380,11 @@
		"text": "ⓢPressonet ⓕMarie ⓑ12"
		}
		},
		"val": {
		"val-page_1-line_1": {
		"dev": {
		"dev-page_1-line_1": {
		"dataset_id": "dataset_id",
		"image": {
		"iiif_url": "{FIXTURES}/extraction/images/val-page_1-line_1.jpg",
		"iiif_url": "{FIXTURES}/extraction/images/dev-page_1-line_1.jpg",
		"polygon": [
		[
		0,
		@@ -410,10 +410,10 @@
		},
		"text": "ⓢCiraud ⓕAntoine ⓑ34"
		},
		"val-page_1-line_2": {
		"dev-page_1-line_2": {
		"dataset_id": "dataset_id",
		"image": {
		"iiif_url": "{FIXTURES}/extraction/images/val-page_1-line_2.jpg",
		"iiif_url": "{FIXTURES}/extraction/images/dev-page_1-line_2.jpg",
		"polygon": [
		[
		0,
		@@ -439,10 +439,10 @@
		},
		"text": "ⓢCiraud ⓕPriser ⓑ34"
		},
		"val-page_1-line_3": {
		"dev-page_1-line_3": {
		"dataset_id": "dataset_id",
		"image": {
		"iiif_url": "{FIXTURES}/extraction/images/val-page_1-line_3.jpg",
		"iiif_url": "{FIXTURES}/extraction/images/dev-page_1-line_3.jpg",
		"polygon": [
		[
		0,

tests/data/prediction/labels.json

+1 −1

Original line number	Diff line number	Diff line
		@@ -3,7 +3,7 @@
		"images/0a56e8b3-95cd-4fa5-a17b-5b0ff9e6ea84.png": "ⓈBellisson ⒻGeorges Ⓑ91 ⓁP ⒸM ⓀCh ⓄPlombier Ⓟ12241",
		"images/0dfe8bcd-ed0b-453e-bf19-cc697012296e.png": "ⓈTemplié ⒻMarcelle Ⓑ93 ⓁJ Ⓚch ⓄE dachyle"
		},
		"val": {
		"dev": {
		"images/2c242f5c-e979-43c4-b6f2-a6d4815b651d.png": "ⓈA ⒻCharles Ⓑ11 ⓁP ⒸC ⓀF ⓄA Ⓟ14331"
		},
		"test": {

tests/data/training/training_dataset/labels.json

+1 −1

Original line number	Diff line number	Diff line
		@@ -3,7 +3,7 @@
		"images/0a34e13a-4ab0-4a91-8d7c-b1d8fee32628.png": "The latter do not regard",
		"images/0a70e14f-feda-4607-989c-36cf581ddff5.png": "At the beginning of"
		},
		"val": {
		"dev": {
		"images/0a576062-303c-4893-a729-c09c92865d31.png": "One can remember with",
		"images/0b2457c8-81f1-4600-84d9-f8bf2822a991.png": "The play was no more"
		},

tests/test_download.py

+9 −9

Original line number	Diff line number	Diff line
		@@ -96,10 +96,10 @@ def test_download(
		"images/train/dataset_id/train-page_2-line_2.jpg": "ⓢTerontussieux ⓕJean ⓑ2",
		"images/train/dataset_id/train-page_2-line_3.jpg": "ⓢPressonet ⓕMarie ⓑ12",
		},
		"val": {
		"images/val/dataset_id/val-page_1-line_1.jpg": "ⓢCirau⁇ ⓕAntoine ⓑ⁇⁇",
		"images/val/dataset_id/val-page_1-line_2.jpg": "ⓢCirau⁇ ⓕPriser ⓑ⁇⁇",
		"images/val/dataset_id/val-page_1-line_3.jpg": "ⓢCirau⁇ ⓕElisa⁇et⁇ ⓑ⁇⁇",
		"dev": {
		"images/dev/dataset_id/dev-page_1-line_1.jpg": "ⓢCirau⁇ ⓕAntoine ⓑ⁇⁇",
		"images/dev/dataset_id/dev-page_1-line_2.jpg": "ⓢCirau⁇ ⓕPriser ⓑ⁇⁇",
		"images/dev/dataset_id/dev-page_1-line_3.jpg": "ⓢCirau⁇ ⓕElisa⁇et⁇ ⓑ⁇⁇",
		},
		},
		)
		@@ -126,10 +126,14 @@ def test_download(
		IMAGE_DIR = output / "images"
		TEST_DIR = IMAGE_DIR / "test" / "dataset_id"
		TRAIN_DIR = IMAGE_DIR / "train" / "dataset_id"
		VAL_DIR = IMAGE_DIR / "val" / "dataset_id"
		VAL_DIR = IMAGE_DIR / "dev" / "dataset_id"

		expected_paths = [
		output / "charset.pkl",
		# Images of dev folder
		VAL_DIR / "dev-page_1-line_1.jpg",
		VAL_DIR / "dev-page_1-line_2.jpg",
		VAL_DIR / "dev-page_1-line_3.jpg",
		# Images of test folder
		TEST_DIR / "test-page_1-line_1.jpg",
		TEST_DIR / "test-page_1-line_2.jpg",
		@@ -145,10 +149,6 @@ def test_download(
		TRAIN_DIR / "train-page_2-line_1.jpg",
		TRAIN_DIR / "train-page_2-line_2.jpg",
		TRAIN_DIR / "train-page_2-line_3.jpg",
		# Images of val folder
		VAL_DIR / "val-page_1-line_1.jpg",
		VAL_DIR / "val-page_1-line_2.jpg",
		VAL_DIR / "val-page_1-line_3.jpg",
		output / "labels.json",
		output / "split.json",
		]

tests/test_evaluate.py

+4 −4

Original line number	Diff line number	Diff line
		@@ -149,7 +149,7 @@ def test_eval_nerval(capsys, evaluate_config):


		@pytest.mark.parametrize(
		"training_res, val_res, test_res",
		"training_res, dev_res, test_res",
		(
		(
		{
		@@ -202,7 +202,7 @@ def test_eval_nerval(capsys, evaluate_config):
		)
		@pytest.mark.parametrize("is_output_json", ((True, False)))
		def test_evaluate(
		capsys, training_res, val_res, test_res, is_output_json, evaluate_config, tmp_path
		capsys, training_res, dev_res, test_res, is_output_json, evaluate_config, tmp_path
		):
		evaluate_path = FIXTURES / "evaluate"

		@@ -224,7 +224,7 @@ def test_evaluate(

		# Check that the evaluation results are correct
		for split_name, expected_res in zip(
		["train", "val", "test"], [training_res, val_res, test_res]
		["train", "dev", "test"], [training_res, dev_res, test_res]
		):
		filename = (
		evaluate_config["training"]["output_folder"]
		@@ -409,7 +409,7 @@ def test_evaluate_language_model(
		},
		),
		(
		"val",
		"dev",
		{
		"nb_chars": 34,
		"cer": 0.0882,

tests/test_language_model.py

+8 −8

Original line number	Diff line number	Diff line
		@@ -114,10 +114,10 @@ def test_language_model(
		"images/train/dataset_id/train-page_2-line_2.jpg": "ⓢTerontussieux ⓕJean ⓑ2",
		"images/train/dataset_id/train-page_2-line_3.jpg": "ⓢPressonet ⓕMarie ⓑ12",
		},
		"val": {
		"images/val/dataset_id/val-page_1-line_1.jpg": "ⓢCirau⁇ ⓕAntoine ⓑ⁇⁇",
		"images/val/dataset_id/val-page_1-line_2.jpg": "ⓢCirau⁇ ⓕPriser ⓑ⁇⁇",
		"images/val/dataset_id/val-page_1-line_3.jpg": "ⓢCirau⁇ ⓕElisa⁇et⁇ ⓑ⁇⁇",
		"dev": {
		"images/dev/dataset_id/dev-page_1-line_1.jpg": "ⓢCirau⁇ ⓕAntoine ⓑ⁇⁇",
		"images/dev/dataset_id/dev-page_1-line_2.jpg": "ⓢCirau⁇ ⓕPriser ⓑ⁇⁇",
		"images/dev/dataset_id/dev-page_1-line_3.jpg": "ⓢCirau⁇ ⓕElisa⁇et⁇ ⓑ⁇⁇",
		},
		},
		)
		@@ -318,10 +318,10 @@ def test_language_model_subword_vocab_size(
		"images/train/dataset_id/train-page_2-line_2.jpg": "ⓢTerontussieux ⓕJean ⓑ2",
		"images/train/dataset_id/train-page_2-line_3.jpg": "ⓢPressonet ⓕMarie ⓑ12",
		},
		"val": {
		"images/val/dataset_id/val-page_1-line_1.jpg": "ⓢCirau⁇ ⓕAntoine ⓑ⁇⁇",
		"images/val/dataset_id/val-page_1-line_2.jpg": "ⓢCirau⁇ ⓕPriser ⓑ⁇⁇",
		"images/val/dataset_id/val-page_1-line_3.jpg": "ⓢCirau⁇ ⓕElisa⁇et⁇ ⓑ⁇⁇",
		"dev": {
		"images/dev/dataset_id/dev-page_1-line_1.jpg": "ⓢCirau⁇ ⓕAntoine ⓑ⁇⁇",
		"images/dev/dataset_id/dev-page_1-line_2.jpg": "ⓢCirau⁇ ⓕPriser ⓑ⁇⁇",
		"images/dev/dataset_id/dev-page_1-line_3.jpg": "ⓢCirau⁇ ⓕElisa⁇et⁇ ⓑ⁇⁇",
		},
		},
		)

Original line number	Diff line number	Diff line
		@@ -25,7 +25,7 @@ This will, for each evaluated split:
		\| `--config` \| Path to the configuration file. \| `pathlib.Path` \| \|
		\| `--nerval-threshold` \| Distance threshold for the match between gold and predicted entity during Nerval evaluation. `0` would impose perfect matches, `1` would allow completely different strings to be considered as a match. \| `float` \| `0.3` \|
		\| `--output-json` \| Where to save evaluation results in JSON format. \| `pathlib.Path` \| `None` \|
		\| `--sets` \| Sets to evaluate. Defaults to `train`, `val`, `test`. \| `list[str]` \| `["train", "val", "test"]` \|
		\| `--sets` \| Sets to evaluate. Defaults to `train`, `dev`, `test`. \| `list[str]` \| `["train", "dev", "test"]` \|

		## Examples

		@@ -37,7 +37,7 @@ This will, for each evaluated split:
		\| Split \| CER (HTR-NER) \| CER (HTR) \| WER (HTR-NER) \| WER (HTR) \| WER (HTR no punct) \|
		\| :---: \| :-----------: \| :-------: \| :-----------: \| :-------: \| :----------------: \|
		\| train \| x \| x \| x \| x \| x \|
		\| val \| x \| x \| x \| x \| x \|
		\| dev \| x \| x \| x \| x \| x \|
		\| test \| x \| x \| x \| x \| x \|

		#### 5 worst prediction(s)
		@@ -57,7 +57,7 @@ This will, for each evaluated split:
		\| Split \| CER (HTR-NER) \| CER (HTR) \| WER (HTR-NER) \| WER (HTR) \| WER (HTR no punct) \| NER \|
		\| :---: \| :-----------: \| :-------: \| :-----------: \| :-------: \| :----------------: \| :-: \|
		\| train \| x \| x \| x \| x \| x \| x \|
		\| val \| x \| x \| x \| x \| x \| x \|
		\| dev \| x \| x \| x \| x \| x \| x \|
		\| test \| x \| x \| x \| x \| x \| x \|

		#### Nerval evaluation
		@@ -69,7 +69,7 @@ This will, for each evaluated split:
		\| Surname \| x \| x \| x \| x \| x \| x \|
		\| All \| x \| x \| x \| x \| x \| x \|

		##### val
		##### dev

		\| tag \| predicted \| matched \| Precision \| Recall \| F1 \| Support \|
		\| :-----: \| :-------: \| :-----: \| :-------: \| :----: \| :-: \| :-----: \|

Original line number	Diff line number	Diff line
		@@ -3,7 +3,7 @@
		\| Split \| CER (HTR-NER) \| CER (HTR) \| WER (HTR-NER) \| WER (HTR) \| WER (HTR no punct) \| NER \|
		\|:-----:\|:-------------:\|:---------:\|:-------------:\|:---------:\|:------------------:\|:----:\|
		\| train \| 18.89 \| 21.05 \| 26.67 \| 26.67 \| 26.67 \| 7.14 \|
		\| val \| 8.82 \| 11.54 \| 50.0 \| 50.0 \| 50.0 \| 0.0 \|
		\| dev \| 8.82 \| 11.54 \| 50.0 \| 50.0 \| 50.0 \| 0.0 \|
		\| test \| 2.78 \| 3.33 \| 14.29 \| 14.29 \| 14.29 \| 0.0 \|

		#### Nerval evaluation
		@@ -22,7 +22,7 @@
		\| Surname \| 2 \| 2 \| 100.0 \| 100.0 \| 100.0 \| 2 \|
		\| ALL \| 15 \| 12 \| 80.0 \| 85.71 \| 82.76 \| 14 \|

		##### val
		##### dev

		\| tag \| predicted \| matched \| Precision \| Recall \| F1 \| Support \|
		\|:----------\|----------:\|--------:\|----------:\|-------:\|------:\|--------:\|

Compare revisions

Source

Target

Commits on Source 2

Files

configs/eval.json

configs/quickstart.json

configs/tests.json

dan/init.py

dan/ocr/mlflow.py

docs/get_started/training.md

docs/usage/datasets/download.md

docs/usage/datasets/language_model.md

docs/usage/evaluate/index.md

docs/usage/train/tensorboard.md

tests/data/analyze/stats.md

tests/data/evaluate/inference.json

tests/data/evaluate/metrics_table.md

tests/data/extraction/elements/val-page_1-line_1.json→tests/data/extraction/elements/dev-page_1-line_1.json

tests/data/extraction/elements/val-page_1-line_2.json→tests/data/extraction/elements/dev-page_1-line_2.json

tests/data/extraction/elements/val-page_1-line_3.json→tests/data/extraction/elements/dev-page_1-line_3.json

tests/data/extraction/elements/val-page_1.json→tests/data/extraction/elements/dev-page_1.json

tests/data/extraction/elements/val.json→tests/data/extraction/elements/dev.json

tests/data/extraction/elements/root.json

tests/data/extraction/images/val-page_1-line_1.jpg→tests/data/extraction/images/dev-page_1-line_1.jpg

tests/data/extraction/images/val-page_1-line_2.jpg→tests/data/extraction/images/dev-page_1-line_2.jpg

tests/data/extraction/images/val-page_1-line_3.jpg→tests/data/extraction/images/dev-page_1-line_3.jpg

tests/data/extraction/split.json

tests/data/prediction/labels.json

tests/data/training/training_dataset/labels.json

tests/test_download.py

tests/test_evaluate.py

tests/test_language_model.py