From 5bbe9593fd7e3fb357bf2eb01f1b3c5549058a9d Mon Sep 17 00:00:00 2001
From: Konstantin Baierer <unixprog@gmail.com>
Date: Mon, 21 Oct 2019 20:31:42 +0200
Subject: [PATCH] add ocrd-tool validation to output
---
kwalitee/repo.py | 8 ++-
repos.json | 170 +++++++++++++++++++++++++++--------------------
2 files changed, 105 insertions(+), 73 deletions(-)
diff --git a/kwalitee/repo.py b/kwalitee/repo.py
index d42f046..1cd08cb 100644
--- a/kwalitee/repo.py
+++ b/kwalitee/repo.py
@@ -59,7 +59,13 @@ class Repo():
desc['name'] = self.name
if files:
desc['files'] = self.get_file_contents()
- desc['ocrd_tool'] = json.loads(desc['files']['ocrd-tool.json']) if desc['files']['ocrd-tool.json'] else None
+ if desc['files']['ocrd-tool.json']:
+ desc['ocrd_tool'] = json.loads(desc['files']['ocrd-tool.json'])
+ with pushd_popd(self.path):
+ desc['ocrd_tool_validate'] = self._run('ocrd ocrd-tool ocrd-tool.json validate').stdout
+ else:
+ desc['ocrd_tool'] = ''
+ desc['ocrd_tool_validate'] = 'NO ocrd-tool.json'
if git:
desc['git'] = self.get_git_stats()
if python:
diff --git a/repos.json b/repos.json
index 24c514e..6f0b921 100644
--- a/repos.json
+++ b/repos.json
@@ -2,44 +2,36 @@
{
"files": {
"Dockerfile": null,
- "README.md": "# ocrd_calamari",
- "ocrd-tool.json": "{\n \"git_url\": \"https://github.com/OCR-D/ocrd_calamari\",\n \"version\": \"0.0.1\",\n \"tools\": {\n \"ocrd-calamari-ocr\": {\n \"executable\": \"ocrd-calamari-ocr\",\n \"categories\": [\n \"Text recognition and optimization\"\n ],\n \"steps\": [\n \"recognition/text-recognition\"\n ],\n \"description\": \"Recognize lines with kraken\",\n \"parameters\": {\n \"checkpoint\": {\"type\": \"string\", \"format\": \"file\", \"cacheable\": true},\n \"processes\": {\"type\": \"number\", \"default\": 1},\n \"batch_size\": {\"type\": \"number\", \"default\": 1},\n \"voter\": {\"type\": \"string\", \"default\": \"confidence_voter_default_ctc\"},\n \"extended_prediction_data_format\": {\"type\": \"string\", \"default\": \"json\"},\n \"XXX output_dir\": \"TODO\",\n \"XXX extended_prediction_data\": \"TODO\"\n }\n }\n }\n}\n",
- "setup.py": null
+ "README.md": "# ocrd_calamari\n\nRecognize text using [Calamari OCR](https://github.com/Calamari-OCR/calamari).\n\n## Introduction\n\nThis offers a OCR-D compliant workspace processor for some of the functionality of Calamari OCR.\n\nThis processor only operates on the text line level and so needs a line segmentation (and by extension a binarized \nimage) as its input.\n\n## Installation\n\n### From PyPI\n\n:construction: :construction: :construction: :construction: :construction: :construction: :construction:\n\n```\npip install ocrd_calamari\n```\n\n### From Repo\n\n```sh\npip install .\n```\n\nTo install the calamari with the GPU version of Tensorflow:\n\n```sh\npip install 'calamari-ocr[tf_cpu]'\npip install .\n```\n\n## Example Usage\n\n~~~\nocrd-calamari-recognize -p test-parameters.json -m mets.xml -I OCR-D-SEG-LINE -O OCR-D-OCR-CALAMARI\n~~~\n\nWith `test-parameters.json`:\n~~~\n{\n \"checkpoint\": \"/path/to/some/trained/models/*.ckpt.json\"\n}\n~~~\n\nTODO\n----\n\n* Support Calamari's \"extended prediction data\" output\n* Currently, the processor only supports a prediction using confidence voting of multiple models. While this is\n superior, it makes sense to support single model prediction, too.\n",
+ "ocrd-tool.json": "{\n \"git_url\": \"https://github.com/kba/ocrd_calamari\",\n \"version\": \"0.0.1\",\n \"tools\": {\n \"ocrd-calamari-recognize\": {\n \"executable\": \"ocrd-calamari-recognize\",\n \"categories\": [\n \"Text recognition and optimization\"\n ],\n \"steps\": [\n \"recognition/text-recognition\"\n ],\n \"description\": \"Recognize lines with Calamari\",\n \"input_file_grp\": [\n \"OCR-D-SEG-LINE\"\n ],\n \"output_file_grp\": [\n \"OCR-D-OCR-CALAMARI\"\n ],\n \"parameters\": {\n \"checkpoint\": {\"type\": \"string\", \"format\": \"file\", \"cacheable\": true},\n \"voter\": {\"type\": \"string\", \"default\": \"confidence_voter_default_ctc\"}\n }\n }\n }\n}\n",
+ "setup.py": "# -*- coding: utf-8 -*-\nimport codecs\n\nfrom setuptools import setup, find_packages\n\nsetup(\n name='ocrd_calamari',\n version='0.0.1',\n description='Calamari bindings',\n long_description=codecs.open('README.md', encoding='utf-8').read(),\n author='Konstantin Baierer, Mike Gerber',\n author_email='unixprog@gmail.com, mike.gerber@sbb.spk-berlin.de',\n url='https://github.com/kba/ocrd_calamari',\n license='Apache License 2.0',\n packages=find_packages(exclude=('tests', 'docs')),\n install_requires=open('requirements.txt').read().split('\\n'),\n package_data={\n '': ['*.json', '*.yml', '*.yaml'],\n },\n entry_points={\n 'console_scripts': [\n 'ocrd-calamari-recognize=ocrd_calamari.cli:ocrd_calamari_recognize',\n ]\n },\n)\n"
},
"git": {
- "last_commit": "Thu Jul 26 19:09:07 2018 +0200",
- "number_of_commits": "2"
+ "last_commit": "Thu Aug 22 14:03:59 2019 +0200",
+ "number_of_commits": "29"
},
"name": "ocrd_calamari",
"ocrd_tool": {
- "git_url": "https://github.com/OCR-D/ocrd_calamari",
+ "git_url": "https://github.com/kba/ocrd_calamari",
"tools": {
- "ocrd-calamari-ocr": {
+ "ocrd-calamari-recognize": {
"categories": [
"Text recognition and optimization"
],
- "description": "Recognize lines with kraken",
- "executable": "ocrd-calamari-ocr",
+ "description": "Recognize lines with Calamari",
+ "executable": "ocrd-calamari-recognize",
+ "input_file_grp": [
+ "OCR-D-SEG-LINE"
+ ],
+ "output_file_grp": [
+ "OCR-D-OCR-CALAMARI"
+ ],
"parameters": {
- "XXX extended_prediction_data": "TODO",
- "XXX output_dir": "TODO",
- "batch_size": {
- "default": 1,
- "type": "number"
- },
"checkpoint": {
"cacheable": true,
"format": "file",
"type": "string"
},
- "extended_prediction_data_format": {
- "default": "json",
- "type": "string"
- },
- "processes": {
- "default": 1,
- "type": "number"
- },
"voter": {
"default": "confidence_voter_default_ctc",
"type": "string"
@@ -52,12 +44,13 @@
},
"version": "0.0.1"
},
+ "ocrd_tool_validate": "<report valid=\"false\">\n <error>[tools.ocrd-calamari-recognize.parameters.checkpoint] 'description' is a required property</error>\n <error>[tools.ocrd-calamari-recognize.parameters.voter] 'description' is a required property</error>\n</report>",
"org_plus_name": "OCR-D/ocrd_calamari",
"python": {
- "author": "",
- "author-email": "",
- "name": "",
- "url": ""
+ "author": "Konstantin Baierer, Mike Gerber",
+ "author-email": "unixprog@gmail.com, mike.gerber@sbb.spk-berlin.de",
+ "name": "ocrd_calamari",
+ "url": "https://github.com/kba/ocrd_calamari"
},
"url": "https://github.com/OCR-D/ocrd_calamari"
},
@@ -69,8 +62,8 @@
"setup.py": null
},
"git": {
- "last_commit": "Tue Jun 26 18:30:04 2018 +0200",
- "number_of_commits": "5"
+ "last_commit": "Wed Jul 18 18:17:27 2018 +0200",
+ "number_of_commits": "6"
},
"name": "ocrd_im6convert",
"ocrd_tool": {
@@ -100,6 +93,7 @@
},
"version": "0.0.1"
},
+ "ocrd_tool_validate": "<report valid=\"false\">\n <error>[tools.ocrd-im6convert] 'input_file_grp' is a required property</error>\n <error>[tools.ocrd-im6convert] 'output_file_grp' is a required property</error>\n <error>[tools.ocrd-im6convert.parameters.output-format] 'description' is a required property</error>\n</report>",
"org_plus_name": "OCR-D/ocrd_im6convert",
"python": {
"author": "",
@@ -112,16 +106,17 @@
{
"files": {
"Dockerfile": null,
- "README.md": "# ocrd_keraslm\nSimple character-based language model using keras\n",
+ "README.md": "# ocrd_keraslm\n character-level language modelling using Keras\n\n\n## Introduction\n\nThis is a tool for statistical _language modelling_ (predicting text from context) with recurrent neural networks. It models probabilities not on the word level but the _character level_ so as to allow open vocabulary processing (avoiding morphology, historic orthography and word segmentation problems). It manages a vocabulary of mapped characters, which can be easily extended by training on more text. Above that, unmapped characters are treated with underspecification.\n\nIn addition to character sequences, (meta-data) context variables can be configured as extra input. \n\n### Architecture\n\nThe model consists of:\n\n0. an input layer: characters are represented as indexes from the vocabulary mapping, in windows of a number `length` of characters,\n1. a character embedding layer: window sequences are converted into dense vectors by looking up the indexes in an embedding weight matrix,\n2. a context embedding layer: context variables are converted into dense vectors by looking up the indexes in an embedding weight matrix, \n3. character and context vector sequences are concatenated,\n4. a number `depth` of hidden layers: each with a number `width` of hidden recurrent units of _LSTM cells_ (Long Short-term Memory) connected on top of each other,\n5. an output layer derived from the transposed character embedding matrix (weight tying): hidden activations are projected linearly to vectors of dimensionality equal to the character vocabulary size, then softmax is applied returning a probability for each possible value of the next character, respectively.\n\n![model graph depiction](model-graph.png \"graph with 1 context variable\")\n\nThe model is trained by feeding windows of text in index representation to the input layer, calculating output and comparing it to the same text shifted backward by 1 character, and represented as unit vectors (\"one-hot coding\") as target. The loss is calculated as the (unweighted) cross-entropy between target and output. Backpropagation yields error gradients for each layer, which is used to iteratively update the weights (stochastic gradient descent).\n\nThis is implemented in [Keras](https://keras.io) with [Tensorflow](https://www.tensorflow.org/) as backend. It automatically uses a fast CUDA-optimized LSTM implementation (Nividia GPU and Tensorflow installation with GPU support, see below), both in learning and in prediction phase, if available.\n\n\n### Modes of operation\n\nNotably, this model (by default) runs _statefully_, i.e. by implicitly passing hidden state from one window (batch of samples) to the next. That way, the context available for predictions can be arbitrarily long (above `length`, e.g. the complete document up to that point), or short (below `length`, e.g. at the start of a text). (However, this is a passive perspective above `length`, because errors are never back-propagated any further in time during gradient-descent training.) This is favourable to stateless mode because all characters can be output in parallel, and no partial windows need to be presented during training (which slows down).\n\nBesides stateful mode, the model can also be run _incrementally_, i.e. by explicitly passing hidden state from the caller. That way, multiple alternative hypotheses can be processed together. This is used for generation (sampling from the model) and alternative decoding (finding the best path through a sequence of alternatives).\n\n### Context conditioning\n\nEvery text has meta-data like time, author, text type, genre, production features (e.g. print vs typewriter vs digital born rich text, OCR version), language, structural element (e.g. title vs heading vs paragraph vs footer vs marginalia), font family (e.g. Antiqua vs Fraktura) and font shape (e.g. bold vs letter-spaced vs italic vs normal) etc. \n\nThis information (however noisy) can be very useful to facilitate stochastic modelling, since language has an extreme diversity and complexity. To that end, models can be conditioned on extra inputs here, termed _context variables_. The model learns to represent these high-dimensional discrete values as low-dimensional continuous vectors (embeddings), also entering the recurrent hidden layers (as a form of simple additive adaptation).\n\n### Underspecification\n\nIndex zero is reserved for unmapped characters (unseen contexts). During training, its embedding vector is regularised to occupy a center position of all mapped characters (all other contexts), and the hidden layers get to see it every now and then by random degradation. At runtime, therefore, some unknown character (some unknown context) represented as zero does not disturb follow-up predictions too much.\n\n\n## Installation\n\nRequired Ubuntu packages:\n\n* Python (``python`` or ``python3``)\n* pip (``python-pip`` or ``python3-pip``)\n* virtualenv (``python-virtualenv`` or ``python3-virtualenv``)\n\nCreate and activate a virtualenv as usual.\n\nIf you need a custom version of ``keras`` or ``tensorflow`` (like [GPU support](https://www.tensorflow.org/install/install_sources)), install them via `pip` now.\n\nTo install Python dependencies and this module, then do:\n```shell\nmake deps install\n```\nWhich is the equivalent of:\n```shell\npip install -r requirements.txt\npip install -e .\n```\n\nUseful environment variables are:\n- ``TF_CPP_MIN_LOG_LEVEL`` (set to `1` to suppress most of Tensorflow's messages\n- ``CUDA_VISIBLE_DEVICES`` (set empty to force CPU even in a GPU installation)\n\n\n## Usage\n\nThis packages has two user interfaces:\n\n### command line interface `keraslm-rate`\n\nTo be used with string arguments and plain-text files.\n\n```shell\nUsage: keraslm-rate [OPTIONS] COMMAND [ARGS]...\n\nOptions:\n --help Show this message and exit.\n\nCommands:\n train train a language model\n test get overall perplexity from language model\n apply get individual probabilities from language model\n generate sample characters from language model\n print-charset Print the mapped characters\n prune-charset Delete one character from mapping\n plot-char-embeddings-similarity\n Paint a heat map of character embeddings\n plot-context-embeddings-similarity\n Paint a heat map of context embeddings\n plot-context-embeddings-projection\n Paint a 2-d PCA projection of context embeddings\n```\n\nExamples:\n```shell\nkeraslm-rate train --width 64 --depth 4 --length 256 --model model_dta_64_4_256.h5 dta_komplett_2017-09-01/txt/*.tcf.txt\nkeraslm-rate generate -m model_dta_64_4_256.h5 --number 6 \"f\u00fcr die Wi\u017f\u017fen\"\nkeraslm-rate apply -m model_dta_64_4_256.h5 \"so sch\u00e4dlich ist es Borkickheile zu pflanzen\"\nkeraslm-rate test -m model_dta_64_4_256.h5 dta_komplett_2017-09-01/txt/grimm_*.tcf.txt\n```\n\n### [OCR-D processor](https://github.com/OCR-D/core) interface `ocrd-keraslm-rate`\n\nTo be used with [PageXML](https://www.primaresearch.org/tools/PAGELibraries) documents in an [OCR-D](https://github.com/OCR-D/spec/) annotation workflow. Input could be anything with a textual annotation (`TextEquiv` on the given `textequiv_level`). The LM rater could be used for both quality control (without alternative decoding, using only each first index `TextEquiv`) and part of post-correction (with `alternative_decoding=True`, finding the best path among `TextEquiv` indexes).\n\n```json\n \"tools\": {\n \"ocrd-keraslm-rate\": {\n \"executable\": \"ocrd-keraslm-rate\",\n \"categories\": [\n \"Text recognition and optimization\"\n ],\n \"steps\": [\n \"recognition/text-recognition\"\n ],\n \"description\": \"Rate elements of the text with a character-level LSTM language model in Keras\",\n \"input_file_grp\": [\n \"OCR-D-OCR-TESS\",\n \"OCR-D-OCR-KRAK\",\n \"OCR-D-OCR-OCRO\",\n \"OCR-D-OCR-CALA\",\n \"OCR-D-OCR-ANY\",\n \"OCR-D-COR-CIS\",\n \"OCR-D-COR-ASV\"\n ],\n \"output_file_grp\": [\n \"OCR-D-COR-LM\"\n ],\n \"parameters\": {\n \"model_file\": {\n \"type\": \"string\",\n \"format\": \"uri\",\n \"content-type\": \"application/x-hdf;subtype=bag\",\n \"description\": \"path of h5py weight/config file for model trained with keraslm\",\n \"required\": true,\n \"cacheable\": true\n },\n \"textequiv_level\": {\n \"type\": \"string\",\n \"enum\": [\"region\", \"line\", \"word\", \"glyph\"],\n \"default\": \"glyph\",\n \"description\": \"PAGE XML hierarchy level to evaluate TextEquiv sequences on\"\n },\n \"alternative_decoding\": {\n \"type\": \"boolean\",\n \"description\": \"whether to process all TextEquiv alternatives, finding the best path via beam search, and delete each non-best alternative\",\n \"default\": true\n },\n \"beam_width\": {\n \"type\": \"number\",\n \"format\": \"integer\",\n \"description\": \"maximum number of best partial paths to consider during search with alternative_decoding\",\n \"default\": 100\n }\n }\n }\n }\n```\n\nExamples:\n```shell\nmake deps-test # installs ocrd_tesserocr\nmake test/assets # downloads GT, imports PageXML, builds workspaces\nocrd workspace clone -a test/assets/kant_aufklaerung_1784/mets.xml ws1\ncd ws1\nocrd-tesserocr-segment-region -I OCR-D-IMG -O OCR-D-SEG-BLOCK\nocrd-tesserocr-segment-line -I OCR-D-SEG-BLOCK -O OCR-D-SEG-LINE\nocrd-tesserocr-recognize -I OCR-D-SEG-LINE -O OCR-D-OCR-TESS-WORD -p '{ \"textequiv_level\" : \"word\", \"model\" : \"Fraktur\" }'\nocrd-tesserocr-recognize -I OCR-D-SEG-LINE -O OCR-D-OCR-TESS-GLYPH -p '{ \"textequiv_level\" : \"glyph\", \"model\" : \"deu-frak\" }'\n# get confidences and perplexity:\nocrd-keraslm-rate -I OCR-D-OCR-TESS-WORD -O OCR-D-OCR-LM-WORD -p '{ \"model_file\": \"model_dta_64_4_256.h5\", \"textequiv_level\": \"word\", \"alternative_decoding\": false }'\n# also get best path:\nocrd-keraslm-rate -I OCR-D-OCR-TESS-GLYPH -O OCR-D-OCR-LM-GLYPH -p '{ \"model_file\": \"model_dta_64_4_256.h5\", \"textequiv_level\": \"glyph\", \"alternative_decoding\": true, \"beam_width\": 10 }'\n```\n\n## Testing\n\n```shell\nmake deps-test test\n```\nWhich is the equivalent of:\n```shell\npip install -r requirements_test.txt\ntest -e test/assets || test/prepare_gt.bash test/assets\ntest -f model_dta_test.h5 || keraslm-rate train -m model_dta_test.h5 test/assets/*.txt\nkeraslm-rate test -m model_dta_test.h5 test/assets/*.txt\npython -m pytest test $(PYTEST_ARGS)\n```\n\nSet `PYTEST_ARGS=\"-s --verbose\"` to see log output (`-s`) and individual test results (`--verbose`).\n",
"ocrd-tool.json": null,
- "setup.py": "# -*- coding: utf-8 -*-\n\"\"\"\nInstalls:\n - keraslm-rate\n\"\"\"\nimport codecs\n\nfrom setuptools import setup, find_packages\n\nwith codecs.open('README.md', encoding='utf-8') as f:\n README = f.read()\n\nsetup(\n name='ocrd_keraslm',\n version='0.0.1',\n description='keras language model',\n long_description=README,\n author='Konstantin Baierer, Kay-Michael W\u00fcrzner',\n author_email='unixprog@gmail.com, wuerzner@gmail.com',\n url='https://github.com/OCR-D/ocrd_keraslm',\n license='Apache License 2.0',\n packages=find_packages(exclude=('tests', 'docs')),\n install_requires=[\n 'ocrd >= 0.4.0',\n 'keras',\n 'click',\n 'numpy',\n 'tensorflow',\n ],\n package_data={\n '': ['*.json', '*.yml', '*.yaml'],\n },\n entry_points={\n 'console_scripts': [\n 'keraslm-rate=ocrd_keraslm.scripts.run:cli',\n 'ocrd-keraslm-rate=ocrd_keraslm.wrapper.cli:ocrd_keraslm_rate',\n ]\n },\n)\n"
+ "setup.py": "# -*- coding: utf-8 -*-\n\"\"\"\nInstalls:\n - keraslm-rate\n\"\"\"\nimport codecs\n\nfrom setuptools import setup, find_packages\n\nwith codecs.open('README.md', encoding='utf-8') as f:\n README = f.read()\n\nsetup(\n name='ocrd_keraslm',\n version='0.3.1',\n description='character-level language modelling in Keras',\n long_description=README,\n author='Konstantin Baierer, Kay-Michael W\u00fcrzner',\n author_email='unixprog@gmail.com, wuerzner@gmail.com',\n url='https://github.com/OCR-D/ocrd_keraslm',\n license='Apache License 2.0',\n packages=find_packages(exclude=('tests', 'docs')),\n install_requires=[\n 'ocrd >= 0.15.2',\n 'keras',\n 'click',\n 'numpy',\n 'tensorflow',\n 'h5py',\n 'networkx',\n ],\n extras_require={\n 'plotting': [\n 'sklearn',\n 'matplotlib',\n ]\n },\n package_data={\n '': ['*.json', '*.yml', '*.yaml'],\n },\n entry_points={\n 'console_scripts': [\n 'keraslm-rate=ocrd_keraslm.scripts.run:cli',\n 'ocrd-keraslm-rate=ocrd_keraslm.wrapper.cli:ocrd_keraslm_rate',\n ]\n },\n)\n"
},
"git": {
- "last_commit": "Wed Jul 18 11:20:20 2018 +0200",
- "number_of_commits": "20"
+ "last_commit": "Fri Jul 19 13:01:17 2019 +0200",
+ "number_of_commits": "75"
},
"name": "ocrd_keraslm",
- "ocrd_tool": null,
+ "ocrd_tool": "",
+ "ocrd_tool_validate": "NO ocrd-tool.json",
"org_plus_name": "OCR-D/ocrd_keraslm",
"python": {
"author": "Konstantin Baierer, Kay-Michael W\u00fcrzner",
@@ -133,14 +128,14 @@
},
{
"files": {
- "Dockerfile": "FROM ocrd/core\nMAINTAINER OCR-D\nENV DEBIAN_FRONTEND noninteractive\nENV PYTHONIOENCODING utf8\nENV LC_ALL C.UTF-8\nENV LANG C.UTF-8\n\nWORKDIR /build-ocrd\nCOPY setup.py .\nCOPY requirements.txt .\nCOPY README.rst .\nRUN apt-get update && \\\n apt-get -y install --no-install-recommends \\\n ca-certificates \\\n make \\\n git\nCOPY ocrd_kraken ./ocrd_kraken\nRUN pip3 install --upgrade pip\nRUN make deps-pip install\n\nENTRYPOINT [\"/bin/sh\", \"-c\"]\n",
+ "Dockerfile": "FROM ocrd/core\nMAINTAINER OCR-D\nENV DEBIAN_FRONTEND noninteractive\nENV PYTHONIOENCODING utf8\nENV LC_ALL C.UTF-8\nENV LANG C.UTF-8\n\nWORKDIR /build-ocrd\nCOPY setup.py .\nCOPY requirements.txt .\nRUN apt-get update && \\\n apt-get -y install --no-install-recommends \\\n ca-certificates \\\n make \\\n git\nCOPY ocrd_kraken ./ocrd_kraken\nRUN pip3 install --upgrade pip\nRUN pip3 install .\n\nENTRYPOINT [\"/bin/sh\", \"-c\"]\n",
"README.md": "# ocrd_kraken\n\n> Wrapper for the kraken OCR engine\n\n[](https://travis-ci.org/OCR-D/ocrd_kraken)\n[](https://hub.docker.com/r/ocrd/kraken/tags/)\n[](https://circleci.com/gh/OCR-D/ocrd_kraken)\n",
"ocrd-tool.json": "{\n \"git_url\": \"https://github.com/OCR-D/ocrd_kraken\",\n \"version\": \"0.0.2\",\n \"tools\": {\n \"ocrd-kraken-binarize\": {\n \"executable\": \"ocrd-kraken-binarize\",\n \"input_file_grp\": \"OCR-D-IMG\",\n \"output_file_grp\": \"OCR-D-IMG-BIN\",\n \"categories\": [\n \"Image preprocessing\"\n ],\n \"steps\": [\n \"preprocessing/optimization/binarization\"\n ],\n \"description\": \"Binarize images with kraken\",\n \"parameters\": {\n \"level-of-operation\": {\n \"type\": \"string\",\n \"default\": \"page\",\n \"enum\": [\"page\", \"block\", \"line\"]\n }\n }\n },\n \"ocrd-kraken-segment\": {\n \"executable\": \"ocrd-kraken-segment\",\n \"categories\": [\n \"Layout analysis\"\n ],\n \"steps\": [\n \"layout/segmentation/region\"\n ],\n \"description\": \"Block segmentation with kraken\",\n \"parameters\": {\n \"text_direction\": {\n \"type\": \"string\",\n \"description\": \"Sets principal text direction\",\n \"enum\": [\"horizontal-lr\", \"horizontal-rl\", \"vertical-lr\", \"vertical-rl\"],\n \"default\": \"horizontal-lr\"\n },\n \"script_detect\": {\n \"type\": \"boolean\",\n \"description\": \"Enable script detection on segmenter output\",\n \"default\": false\n },\n \"maxcolseps\": {\"type\": \"number\", \"format\": \"integer\", \"default\": 2},\n \"scale\": {\"type\": \"number\", \"format\": \"float\", \"default\": null},\n \"black_colseps\": {\"type\": \"boolean\", \"default\": false},\n \"white_colseps\": {\"type\": \"boolean\", \"default\": false}\n }\n },\n \"ocrd-kraken-ocr\": {\n \"executable\": \"ocrd-kraken-ocr\",\n \"categories\": [\"Text recognition and optimization\"],\n \"steps\": [\n \"recognition/text-recognition\"\n ],\n \"description\": \"OCR with kraken\",\n \"parameters\": {\n \"lines-json\": {\n \"type\": \"string\",\n \"format\": \"url\",\n \"required\": \"true\",\n \"description\": \"URL to line segmentation in JSON\"\n }\n }\n }\n\n }\n}\n",
- "setup.py": "# -*- coding: utf-8 -*-\n\"\"\"\nInstalls two binaries:\n\n - ocrd-kraken-binarize\n - ocrd-kraken-segment\n\"\"\"\nimport codecs\n\nfrom setuptools import setup, find_packages\n\nsetup(\n name='ocrd_kraken',\n version='0.1.0',\n description='kraken bindings',\n long_description=codecs.open('README.md', encoding='utf-8').read(),\n long_description_content_type='text/markdown',\n author='Konstantin Baierer, Kay-Michael W\u00fcrzner',\n author_email='unixprog@gmail.com, wuerzner@gmail.com',\n url='https://github.com/OCR-D/ocrd_kraken',\n license='Apache License 2.0',\n packages=find_packages(exclude=('tests', 'docs')),\n install_requires=[\n 'ocrd >= 1.0.0a4',\n 'kraken == 0.9.16',\n 'click >= 7',\n ],\n package_data={\n '': ['*.json', '*.yml', '*.yaml'],\n },\n entry_points={\n 'console_scripts': [\n 'ocrd-kraken-binarize=ocrd_kraken.cli:ocrd_kraken_binarize',\n 'ocrd-kraken-segment=ocrd_kraken.cli:ocrd_kraken_segment',\n ]\n },\n)\n"
+ "setup.py": "# -*- coding: utf-8 -*-\n\"\"\"\nInstalls two binaries:\n\n - ocrd-kraken-binarize\n - ocrd-kraken-segment\n\"\"\"\nimport codecs\n\nfrom setuptools import setup, find_packages\n\nsetup(\n name='ocrd_kraken',\n version='0.1.1',\n description='kraken bindings',\n long_description=codecs.open('README.md', encoding='utf-8').read(),\n long_description_content_type='text/markdown',\n author='Konstantin Baierer, Kay-Michael W\u00fcrzner',\n author_email='unixprog@gmail.com, wuerzner@gmail.com',\n url='https://github.com/OCR-D/ocrd_kraken',\n license='Apache License 2.0',\n packages=find_packages(exclude=('tests', 'docs')),\n install_requires=[\n 'ocrd >= 1.0.0a4',\n 'kraken == 0.9.16',\n 'click >= 7',\n ],\n package_data={\n '': ['*.json', '*.yml', '*.yaml'],\n },\n entry_points={\n 'console_scripts': [\n 'ocrd-kraken-binarize=ocrd_kraken.cli:ocrd_kraken_binarize',\n 'ocrd-kraken-segment=ocrd_kraken.cli:ocrd_kraken_segment',\n ]\n },\n)\n"
},
"git": {
- "last_commit": "Thu Feb 28 10:37:14 2019 +0100",
- "number_of_commits": "80"
+ "last_commit": "Mon Oct 21 20:19:00 2019 +0200",
+ "number_of_commits": "84"
},
"name": "ocrd_kraken",
"ocrd_tool": {
@@ -236,6 +231,7 @@
},
"version": "0.0.2"
},
+ "ocrd_tool_validate": "<report valid=\"false\">\n <error>[tools.ocrd-kraken-binarize.input_file_grp] 'OCR-D-IMG' is not of type 'array'</error>\n <error>[tools.ocrd-kraken-binarize.output_file_grp] 'OCR-D-IMG-BIN' is not of type 'array'</error>\n <error>[tools.ocrd-kraken-binarize.parameters.level-of-operation] 'description' is a required property</error>\n <error>[tools.ocrd-kraken-segment] 'input_file_grp' is a required property</error>\n <error>[tools.ocrd-kraken-segment] 'output_file_grp' is a required property</error>\n <error>[tools.ocrd-kraken-segment.parameters.maxcolseps] 'description' is a required property</error>\n <error>[tools.ocrd-kraken-segment.parameters.scale] 'description' is a required property</error>\n <error>[tools.ocrd-kraken-segment.parameters.black_colseps] 'description' is a required property</error>\n <error>[tools.ocrd-kraken-segment.parameters.white_colseps] 'description' is a required property</error>\n <error>[tools.ocrd-kraken-ocr] 'input_file_grp' is a required property</error>\n <error>[tools.ocrd-kraken-ocr] 'output_file_grp' is a required property</error>\n <error>[tools.ocrd-kraken-ocr.parameters.lines-json.required] 'true' is not of type 'boolean'</error>\n</report>",
"org_plus_name": "OCR-D/ocrd_kraken",
"python": {
"author": "Konstantin Baierer, Kay-Michael W\u00fcrzner",
@@ -247,14 +243,14 @@
},
{
"files": {
- "Dockerfile": "FROM ocrd/core\nMAINTAINER OCR-D\nENV DEBIAN_FRONTEND noninteractive\nENV PYTHONIOENCODING utf8\nENV LC_ALL C.UTF-8\nENV LANG C.UTF-8\n\nWORKDIR /build-ocrd\nCOPY setup.py .\nCOPY requirements.txt .\nCOPY README.md .\nRUN apt-get update && \\\n apt-get -y install --no-install-recommends \\\n ca-certificates \\\n make \\\n git\nCOPY ocrd_ocropy ./ocrd_ocropy\nRUN pip3 install --upgrade pip\nRUN make deps install\n\nENTRYPOINT [\"/bin/sh\", \"-c\"]\n",
+ "Dockerfile": "FROM ocrd/core\nMAINTAINER OCR-D\nENV DEBIAN_FRONTEND noninteractive\nENV PYTHONIOENCODING utf8\nENV LC_ALL C.UTF-8\nENV LANG C.UTF-8\n\nWORKDIR /build-ocrd\nCOPY setup.py .\nCOPY requirements.txt .\nCOPY README.rst .\nRUN apt-get update && \\\n apt-get -y install --no-install-recommends \\\n ca-certificates \\\n make \\\n git\nCOPY ocrd_ocropy ./ocrd_ocropy\nRUN pip3 install --upgrade pip\nRUN make deps-pip install\n\nENTRYPOINT [\"/bin/sh\", \"-c\"]\n",
"README.md": "# ocrd_ocropy\n\n[](https://travis-ci.org/OCR-D/ocrd_ocropy)\n\n[](https://hub.docker.com/r/ocrd/ocropy/tags/)\n\n> Wrapper for the ocropy OCR engine\n",
"ocrd-tool.json": "{\n \"version\": \"0.0.1\",\n \"git_url\": \"https://github.com/OCR-D/ocrd_ocropy\",\n \"tools\": {\n \"ocrd-ocropy-segment\": {\n \"executable\": \"ocrd-ocropy-segment\",\n \"categories\": [\"Image preprocessing\"],\n \"steps\": [\"layout/segmentation/region\"],\n \"description\": \"Segment page\",\n \"input_file_grp\": [\"OCR-D-IMG-BIN\"],\n \"output_file_grp\": [\"OCR-D-SEG-LINE\"],\n \"parameters\": {\n \"maxcolseps\": {\"type\": \"number\", \"description\": \"has an effect\", \"default\": 3},\n \"maxseps\": {\"type\": \"number\", \"description\": \"has an effect\", \"default\": 0},\n \"sepwiden\": {\"type\": \"number\", \"description\": \"has an effect\", \"default\": 10},\n \"csminheight\": {\"type\": \"number\", \"description\": \"has an effect\", \"default\": 10},\n \"csminaspect\": {\"type\": \"number\", \"description\": \"has an effect\", \"default\": 1.1},\n \"pad\": {\"type\": \"number\", \"description\": \"has an effect\", \"default\": 3},\n \"expand\": {\"type\": \"number\", \"description\": \"has an effect\", \"default\": 3},\n \"usegauss\": {\"type\": \"boolean\",\"description\": \"has an effect\", \"default\": false},\n \"threshold\": {\"type\": \"number\", \"description\": \"has an effect\", \"default\": 0.2},\n \"noise\": {\"type\": \"number\", \"description\": \"has an effect\", \"default\": 8},\n \"scale\": {\"type\": \"number\", \"description\": \"has an effect\", \"default\": 0.0},\n \"hscale\": {\"type\": \"number\", \"description\": \"has an effect\", \"default\": 1.0},\n \"vscale\": {\"type\": \"number\", \"description\": \"has an effect\", \"default\": 1.0}\n }\n }\n }\n}\n",
- "setup.py": "# -*- coding: utf-8 -*-\n\"\"\"\nInstalls one binary:\n\n - ocrd-ocropy-segment\n\"\"\"\nimport codecs\n\nfrom setuptools import setup\n\nsetup(\n name='ocrd_ocropy',\n version='0.0.3',\n description='ocropy bindings',\n long_description=codecs.open('README.md', encoding='utf-8').read(),\n long_description_content_type='text/markdown',\n author='Konstantin Baierer',\n author_email='unixprog@gmail.com, wuerzner@gmail.com',\n url='https://github.com/OCR-D/ocrd_ocropy',\n license='Apache License 2.0',\n packages=['ocrd_ocropy'],\n install_requires=[\n 'ocrd >= 1.0.0b8',\n 'ocrd-fork-ocropy >= 1.4.0a3',\n 'click'\n ],\n package_data={\n '': ['*.json', '*.yml', '*.yaml'],\n },\n entry_points={\n 'console_scripts': [\n 'ocrd-ocropy-segment=ocrd_ocropy.cli:ocrd_ocropy_segment',\n ]\n },\n)\n"
+ "setup.py": "# -*- coding: utf-8 -*-\n\"\"\"\nInstalls one binary:\n\n - ocrd-ocropy-segment\n\"\"\"\nimport codecs\n\nfrom setuptools import setup\n\nsetup(\n name='ocrd_ocropy',\n version='0.0.1a1',\n description='ocropy bindings',\n long_description=codecs.open('README.md', encoding='utf-8').read(),\n long_description_content_type='text/markdown',\n author='Konstantin Baierer',\n author_email='unixprog@gmail.com, wuerzner@gmail.com',\n url='https://github.com/OCR-D/ocrd_ocropy',\n license='Apache License 2.0',\n packages=['ocrd_ocropy'],\n install_requires=[\n 'ocrd >= 1.0.0b6',\n 'ocrd-fork-ocropy >= 1.4.0a3',\n 'click'\n ],\n package_data={\n '': ['*.json', '*.yml', '*.yaml'],\n },\n entry_points={\n 'console_scripts': [\n 'ocrd-ocropy-segment=ocrd_ocropy.cli:ocrd_ocropy_segment',\n ]\n },\n)\n"
},
"git": {
- "last_commit": "Tue Jun 11 14:51:00 2019 +0200",
- "number_of_commits": "66"
+ "last_commit": "Thu Feb 28 16:30:26 2019 +0100",
+ "number_of_commits": "60"
},
"name": "ocrd_ocropy",
"ocrd_tool": {
@@ -346,6 +342,7 @@
},
"version": "0.0.1"
},
+ "ocrd_tool_validate": "<report valid=\"true\">\n</report>",
"org_plus_name": "OCR-D/ocrd_ocropy",
"python": {
"author": "Konstantin Baierer",
@@ -358,29 +355,48 @@
{
"files": {
"Dockerfile": null,
- "README.md": "# ocrd_olena\n\n> Bundle olena as an OCR-D tool\n\n## Installation\n\n```\nmake build-olena\n```\n\nWill download and build olena/scribo from source\n",
- "ocrd-tool.json": "{\n \"version\": \"0.0.1\",\n \"git_url\": \"https://github.com/OCR-D/ocrd_ocrevaluation\",\n \"tools\": {\n \"ocrd-olena-sauvola\": {\n \"executable\": \"ocrd-olena-binarize\",\n \"description\": \"OLENA's binarization algos for OCR-D\",\n \"categories\": [\n \"Image preprocessing\"\n ],\n \"steps\": [\n \"preprocessing/optimization/binarization\"\n ],\n \"parameters\": {\n \"impl\": {\n \"description\": \"The name of the actual binarization algorithm\",\n \"type\": \"string\",\n \"required\": true,\n \"enum\": [\"sauvola\"]\n },\n \"win-size\": {\n \"description\": \"Window size\",\n \"type\": \"number\",\n \"format\": \"integer\",\n \"default\": 101\n },\n \"k\": {\n \"description\": \"Sauvola's formulae parameter\",\n \"format\": \"float\",\n \"type\": \"number\",\n \"default\": 0.34\n }\n }\n }\n }\n}\n",
+ "README.md": "# ocrd_olena\n\n> Bundle olena as an OCR-D tool\n\n[](https://travis-ci.org/OCR-D/ocrd_olena)\n\n## Requirements\n\n```\nmake deps-ubuntu\n```\n\n...will try to install the required packages on Ubuntu.\n\n## Installation\n\n```\nmake install\n```\n\n...will download, patch and build olena/scribo from source, and install locally (in a path relative to the CWD).\n\n## Testing\n\n```\nmake test\n```\n\n...will clone the assets repository from Github, make a workspace copy, and run checksum tests for binarization on them.\n\n## Usage\n\nThis package has the following user interfaces:\n\n### [OCR-D processor](https://github.com/OCR-D/core) interface `ocrd-olena-binarize`\n\nTo be used with [PageXML](https://www.primaresearch.org/tools/PAGELibraries) documents in an [OCR-D](https://github.com/OCR-D/spec/) annotation workflow. Input could be any valid workspace with source images available. Currently covers the `Page` hierarchy level only. Uses either (the last) `AlternativeImage`, if any, or `imageFilename`, otherwise. Adds an `AlternativeImage` with the result of binarization for every page.\n\n```json\n \"ocrd-olena-binarize\": {\n \"executable\": \"ocrd-olena-binarize\",\n \"description\": \"OLENA's binarization algos for OCR-D (on page-level)\",\n \"categories\": [\n \"Image preprocessing\"\n ],\n \"steps\": [\n \"preprocessing/optimization/binarization\"\n ],\n \"input_file_grp\": [\n \"OCR-D-SEG-BLOCK\",\n \"OCR-D-SEG-LINE\",\n \"OCR-D-SEG-WORD\",\n \"OCR-D-IMG\"\n ],\n \"output_file_grp\": [\n \"OCR-D-SEG-BLOCK\",\n \"OCR-D-SEG-LINE\",\n \"OCR-D-SEG-WORD\"\n ],\n \"parameters\": {\n \"impl\": {\n \"description\": \"The name of the actual binarization algorithm\",\n \"type\": \"string\",\n \"required\": true,\n \"enum\": [\"sauvola\", \"sauvola-ms\", \"sauvola-ms-fg\", \"sauvola-ms-split\", \"kim\", \"wolf\", \"niblack\", \"singh\", \"otsu\"]\n },\n \"win-size\": {\n \"description\": \"Window size\",\n \"type\": \"number\",\n \"format\": \"integer\",\n \"default\": 101\n },\n \"k\": {\n \"description\": \"Sauvola's formulae parameter\",\n \"format\": \"float\",\n \"type\": \"number\",\n \"default\": 0.34\n }\n }\n }\n```\n",
+ "ocrd-tool.json": "{\n \"version\": \"0.0.2\",\n \"git_url\": \"https://github.com/OCR-D/ocrd_olena\",\n \"tools\": {\n \"ocrd-olena-binarize\": {\n \"executable\": \"ocrd-olena-binarize\",\n \"description\": \"OLENA's binarization algos for OCR-D (on page-level)\",\n \"categories\": [\n \"Image preprocessing\"\n ],\n \"steps\": [\n \"preprocessing/optimization/binarization\"\n ],\n \"input_file_grp\": [\n \"OCR-D-SEG-BLOCK\",\n \"OCR-D-SEG-LINE\",\n \"OCR-D-SEG-WORD\",\n \"OCR-D-IMG\"\n ],\n \"output_file_grp\": [\n \"OCR-D-SEG-BLOCK\",\n \"OCR-D-SEG-LINE\",\n \"OCR-D-SEG-WORD\"\n ],\n \"parameters\": {\n \"impl\": {\n \"description\": \"The name of the actual binarization algorithm\",\n \"type\": \"string\",\n \"required\": true,\n \"enum\": [\"sauvola\", \"sauvola-ms\", \"sauvola-ms-fg\", \"sauvola-ms-split\", \"kim\", \"wolf\", \"niblack\", \"singh\", \"otsu\"]\n },\n \"win-size\": {\n \"description\": \"Window size\",\n \"type\": \"number\",\n \"format\": \"integer\",\n \"default\": 101\n },\n \"k\": {\n \"description\": \"Sauvola's formulae parameter\",\n \"format\": \"float\",\n \"type\": \"number\",\n \"default\": 0.34\n }\n }\n }\n }\n}\n",
"setup.py": null
},
"git": {
- "last_commit": "Mon Jun 25 11:52:38 2018 +0200",
- "number_of_commits": "13"
+ "last_commit": "Mon Sep 9 22:21:57 2019 +0200",
+ "number_of_commits": "47"
},
"name": "ocrd_olena",
"ocrd_tool": {
- "git_url": "https://github.com/OCR-D/ocrd_ocrevaluation",
+ "git_url": "https://github.com/OCR-D/ocrd_olena",
"tools": {
- "ocrd-olena-sauvola": {
+ "ocrd-olena-binarize": {
"categories": [
"Image preprocessing"
],
- "description": "OLENA's binarization algos for OCR-D",
+ "description": "OLENA's binarization algos for OCR-D (on page-level)",
"executable": "ocrd-olena-binarize",
+ "input_file_grp": [
+ "OCR-D-SEG-BLOCK",
+ "OCR-D-SEG-LINE",
+ "OCR-D-SEG-WORD",
+ "OCR-D-IMG"
+ ],
+ "output_file_grp": [
+ "OCR-D-SEG-BLOCK",
+ "OCR-D-SEG-LINE",
+ "OCR-D-SEG-WORD"
+ ],
"parameters": {
"impl": {
"description": "The name of the actual binarization algorithm",
"enum": [
- "sauvola"
+ "sauvola",
+ "sauvola-ms",
+ "sauvola-ms-fg",
+ "sauvola-ms-split",
+ "kim",
+ "wolf",
+ "niblack",
+ "singh",
+ "otsu"
],
"required": true,
"type": "string"
@@ -403,8 +419,9 @@
]
}
},
- "version": "0.0.1"
+ "version": "0.0.2"
},
+ "ocrd_tool_validate": "<report valid=\"true\">\n</report>",
"org_plus_name": "OCR-D/ocrd_olena",
"python": {
"author": "",
@@ -476,6 +493,7 @@
},
"version": "0.0.1"
},
+ "ocrd_tool_validate": "<report valid=\"false\">\n <error>[tools.ocrd-segment-evaluate] 'output_file_grp' is a required property</error>\n</report>",
"org_plus_name": "OCR-D/ocrd_segment",
"python": {
"author": "Konstantin Baierer, Kay-Michael W\u00fcrzner, Robert Sachunsky",
@@ -489,12 +507,12 @@
"files": {
"Dockerfile": "FROM ocrd/core\nMAINTAINER OCR-D\nENV DEBIAN_FRONTEND noninteractive\nENV PYTHONIOENCODING utf8\nENV LC_ALL C.UTF-8\nENV LANG C.UTF-8\n\nWORKDIR /build-ocrd\nCOPY setup.py .\nCOPY requirements.txt .\nCOPY requirements_test.txt .\nCOPY README.rst .\nCOPY LICENSE .\nRUN apt-get update && \\\n apt-get -y install --no-install-recommends \\\n ca-certificates \\\n make \\\n git\nCOPY Makefile .\nRUN make deps-ubuntu\nCOPY ocrd_tesserocr ./ocrd_tesserocr\nRUN pip3 install --upgrade pip\nRUN make PYTHON=python3 PIP=pip3 deps install\nCOPY test ./test\nRUN make PYTHON=python3 PIP=pip3 deps-test\n\nENTRYPOINT [\"/bin/sh\", \"-c\"]\n",
"README.md": null,
- "ocrd-tool.json": "{\n \"version\": \"0.4.1\",\n \"git_url\": \"https://github.com/OCR-D/ocrd_tesserocr\",\n \"dockerhub\": \"ocrd/tesserocr\",\n \"tools\": {\n \"ocrd-tesserocr-deskew\": {\n \"executable\": \"ocrd-tesserocr-deskew\",\n \"categories\": [\"Image preprocessing\"],\n \"description\": \"Deskew pages or regions\",\n \"input_file_grp\": [\n \"OCR-D-IMG\",\n \"OCR-D-SEG-BLOCK\"\n ],\n \"output_file_grp\": [\n \"OCR-D-DESKEW-BLOCK\"\n ],\n \"steps\": [\"preprocessing/optimization/deskewing\"],\n \"parameters\": {\n \"operation_level\": {\n \"type\": \"string\",\n \"enum\": [\"page\",\"region\"],\n \"default\": \"region\",\n \"description\": \"PAGE XML hierarchy level to operate on\"\n }\n }\n },\n \"ocrd-tesserocr-recognize\": {\n \"executable\": \"ocrd-tesserocr-recognize\",\n \"categories\": [\"Text recognition and optimization\"],\n \"description\": \"Recognize text in lines with tesseract\",\n \"input_file_grp\": [\n \"OCR-D-SEG-BLOCK\",\n \"OCR-D-SEG-LINE\",\n \"OCR-D-SEG-WORD\",\n \"OCR-D-SEG-GLYPH\"\n ],\n \"output_file_grp\": [\n \"OCR-D-OCR-TESS\"\n ],\n \"steps\": [\"recognition/text-recognition\"],\n \"parameters\": {\n \"textequiv_level\": {\n \"type\": \"string\",\n \"enum\": [\"region\", \"line\", \"word\", \"glyph\"],\n \"default\": \"line\",\n \"description\": \"PAGE XML hierarchy level to add the TextEquiv results to (requires existing layout annotation up to one level above that)\"\n },\n \"overwrite_words\": {\n \"type\": \"boolean\",\n \"default\": false,\n \"description\": \"remove existing layout and text annotation below the TextLine level (regardless of textequiv_level)\"\n },\n \"model\": {\n \"type\": \"string\",\n \"description\": \"tessdata model to apply (an ISO 639-3 language specification or some other basename, e.g. deu-frak or Fraktur)\"\n }\n }\n },\n \"ocrd-tesserocr-segment-region\": {\n \"executable\": \"ocrd-tesserocr-segment-region\",\n \"categories\": [\"Layout analysis\"],\n \"description\": \"Segment regions into lines with tesseract\",\n \"input_file_grp\": [\n \"OCR-D-IMG\"\n ],\n \"output_file_grp\": [\n \"OCR-D-SEG-BLOCK\"\n ],\n \"steps\": [\"layout/segmentation/region\"],\n \"parameters\": {\n \"overwrite_regions\": {\n \"type\": \"boolean\",\n \"default\": true,\n \"description\": \"remove existing layout and text annotation below the Page level\"\n },\n \"padding\": {\n \"type\": \"number\",\n \"format\": \"integer\",\n \"description\": \"extend detected region rectangles by this many (true) pixels\",\n \"default\": 8\n },\n \"crop_polygons\": {\n \"type\": \"boolean\",\n \"default\": false,\n \"description\": \"annotate polygon coordinates instead of rectangles, and create cropped AlternativeImage masked by the polygon outlines\"\n },\n \"find_tables\": {\n \"type\": \"boolean\",\n \"default\": true,\n \"description\": \"recognise table regions (textord_tabfind_find_tables)\"\n }\n }\n },\n \"ocrd-tesserocr-segment-line\": {\n \"executable\": \"ocrd-tesserocr-segment-line\",\n \"categories\": [\"Layout analysis\"],\n \"description\": \"Segment page into regions with tesseract\",\n \"input_file_grp\": [\n \"OCR-D-SEG-BLOCK\"\n ],\n \"output_file_grp\": [\n \"OCR-D-SEG-LINE\"\n ],\n \"steps\": [\"layout/segmentation/line\"],\n \"parameters\": {\n \"overwrite_lines\": {\n \"type\": \"boolean\",\n \"default\": true,\n \"description\": \"remove existing layout and text annotation below the TextRegion level\"\n }\n }\n },\n \"ocrd-tesserocr-segment-word\": {\n \"executable\": \"ocrd-tesserocr-segment-word\",\n \"categories\": [\"Layout analysis\"],\n \"description\": \"Segment lines into words with tesseract\",\n \"input_file_grp\": [\n \"OCR-D-SEG-LINE\"\n ],\n \"output_file_grp\": [\n \"OCR-D-SEG-WORD\"\n ],\n \"steps\": [\"layout/segmentation/word\"],\n \"parameters\": {\n \"overwrite_words\": {\n \"type\": \"boolean\",\n \"default\": true,\n \"description\": \"remove existing layout and text annotation below the TextLine level\"\n }\n }\n },\n \"ocrd-tesserocr-crop\": {\n \"executable\": \"ocrd-tesserocr-crop\",\n \"categories\": [\"Image preprocessing\"],\n \"description\": \"Poor man's cropping with tesseract\",\n \"input_file_grp\": [\n\t\"OCR-D-IMG\"\n ],\n \"output_file_grp\": [\n\t\"OCR-D-IMG-CROPPED\"\n ],\n \"steps\": [\"preprocessing/optimization/cropping\"],\n \"parameters\" : {\n \"padding\": {\n \"type\": \"number\",\n \"format\": \"integer\",\n \"description\": \"extend detected border by this many (true) pixels on every side\",\n \"default\": 4\n }\n }\n },\n \"ocrd-tesserocr-binarize\": {\n \"executable\": \"ocrd-tesserocr-binarize\",\n \"categories\": [\"Image preprocessing\"],\n \"description\": \"Binarize pages, regions or lines\",\n \"input_file_grp\": [\n \"OCR-D-IMG\",\n \"OCR-D-SEG-BLOCK\",\n \"OCR-D-SEG-LINE\"\n ],\n \"output_file_grp\": [\n \"OCR-D-BIN-BLOCK\",\n \"OCR-D-BIN-LINE\"\n ],\n \"steps\": [\"preprocessing/optimization/binarization\"],\n \"parameters\": {\n \"operation_level\": {\n \"type\": \"string\",\n \"enum\": [\"region\", \"line\"],\n \"default\": \"region\",\n \"description\": \"PAGE XML hierarchy level to operate on\"\n }\n }\n }\n }\n}\n",
- "setup.py": "# -*- coding: utf-8 -*-\n\"\"\"\nInstalls five executables:\n\n - ocrd_tesserocr_recognize\n - ocrd_tesserocr_segment_region\n - ocrd_tesserocr_segment_line\n - ocrd_tesserocr_segment_word\n - ocrd_tesserocr_crop\n - ocrd_tesserocr_deskew\n - ocrd_tesserocr_binarize\n\"\"\"\nimport codecs\n\nfrom setuptools import setup, find_packages\n\nsetup(\n name='ocrd_tesserocr',\n version='0.4.1',\n description='Tesserocr bindings',\n long_description=codecs.open('README.rst', encoding='utf-8').read(),\n author='Konstantin Baierer, Kay-Michael W\u00fcrzner, Robert Sachunsky',\n author_email='unixprog@gmail.com, wuerzner@gmail.com, sachunsky@informatik.uni-leipzig.de',\n url='https://github.com/OCR-D/ocrd_tesserocr',\n license='Apache License 2.0',\n packages=find_packages(exclude=('tests', 'docs')),\n install_requires=open('requirements.txt').read().split('\\n'),\n package_data={\n '': ['*.json', '*.yml', '*.yaml'],\n },\n entry_points={\n 'console_scripts': [\n 'ocrd-tesserocr-recognize=ocrd_tesserocr.cli:ocrd_tesserocr_recognize',\n 'ocrd-tesserocr-segment-region=ocrd_tesserocr.cli:ocrd_tesserocr_segment_region',\n 'ocrd-tesserocr-segment-line=ocrd_tesserocr.cli:ocrd_tesserocr_segment_line',\n 'ocrd-tesserocr-segment-word=ocrd_tesserocr.cli:ocrd_tesserocr_segment_word',\n 'ocrd-tesserocr-crop=ocrd_tesserocr.cli:ocrd_tesserocr_crop',\n 'ocrd-tesserocr-deskew=ocrd_tesserocr.cli:ocrd_tesserocr_deskew',\n 'ocrd-tesserocr-binarize=ocrd_tesserocr.cli:ocrd_tesserocr_binarize',\n ]\n },\n)\n"
+ "ocrd-tool.json": "{\n \"version\": \"0.3.0\",\n \"git_url\": \"https://github.com/OCR-D/ocrd_tesserocr\",\n \"dockerhub\": \"ocrd/tesserocr\",\n \"tools\": {\n \"ocrd-tesserocr-deskew\": {\n \"executable\": \"ocrd-tesserocr-deskew\",\n \"categories\": [\"Image preprocessing\"],\n \"description\": \"Deskew pages or regions\",\n \"input_file_grp\": [\n \"OCR-D-IMG\",\n \"OCR-D-SEG-BLOCK\"\n ],\n \"output_file_grp\": [\n \"OCR-D-DESKEW-BLOCK\"\n ],\n \"steps\": [\"preprocessing/optimization/deskewing\"],\n \"parameters\": {\n \"operation_level\": {\n \"type\": \"string\",\n \"enum\": [\"page\",\"region\"],\n \"default\": \"region\",\n \"description\": \"PAGE XML hierarchy level to operate on\"\n }\n }\n },\n \"ocrd-tesserocr-recognize\": {\n \"executable\": \"ocrd-tesserocr-recognize\",\n \"categories\": [\"Text recognition and optimization\"],\n \"description\": \"Recognize text in lines with tesseract\",\n \"input_file_grp\": [\n \"OCR-D-SEG-BLOCK\",\n \"OCR-D-SEG-LINE\",\n \"OCR-D-SEG-WORD\",\n \"OCR-D-SEG-GLYPH\"\n ],\n \"output_file_grp\": [\n \"OCR-D-OCR-TESS\"\n ],\n \"steps\": [\"recognition/text-recognition\"],\n \"parameters\": {\n \"textequiv_level\": {\n \"type\": \"string\",\n \"enum\": [\"region\", \"line\", \"word\", \"glyph\"],\n \"default\": \"line\",\n \"description\": \"PAGE XML hierarchy level to add the TextEquiv results to (requires existing layout annotation up to one level above that)\"\n },\n \"overwrite_words\": {\n \"type\": \"boolean\",\n \"default\": false,\n \"description\": \"remove existing layout and text annotation below the TextLine level (regardless of textequiv_level)\"\n },\n \"model\": {\n \"type\": \"string\",\n \"description\": \"tessdata model to apply (an ISO 639-3 language specification or some other basename, e.g. deu-frak or Fraktur)\"\n }\n }\n },\n \"ocrd-tesserocr-segment-region\": {\n \"executable\": \"ocrd-tesserocr-segment-region\",\n \"categories\": [\"Layout analysis\"],\n \"description\": \"Segment regions into lines with tesseract\",\n \"input_file_grp\": [\n \"OCR-D-IMG\"\n ],\n \"output_file_grp\": [\n \"OCR-D-SEG-BLOCK\"\n ],\n \"steps\": [\"layout/segmentation/region\"],\n \"parameters\": {\n \"overwrite_regions\": {\n \"type\": \"boolean\",\n \"default\": true,\n \"description\": \"remove existing layout and text annotation below the Page level\"\n },\n \"padding\": {\n \"type\": \"number\",\n \"format\": \"integer\",\n \"description\": \"extend detected region rectangles by this many (true) pixels\",\n \"default\": 8\n },\n \"crop_polygons\": {\n \"type\": \"boolean\",\n \"default\": false,\n \"description\": \"annotate polygon coordinates instead of rectangles, and create cropped AlternativeImage masked by the polygon outlines\"\n },\n \"find_tables\": {\n \"type\": \"boolean\",\n \"default\": true,\n \"description\": \"recognise table regions (textord_tabfind_find_tables)\"\n }\n }\n },\n \"ocrd-tesserocr-segment-line\": {\n \"executable\": \"ocrd-tesserocr-segment-line\",\n \"categories\": [\"Layout analysis\"],\n \"description\": \"Segment page into regions with tesseract\",\n \"input_file_grp\": [\n \"OCR-D-SEG-BLOCK\"\n ],\n \"output_file_grp\": [\n \"OCR-D-SEG-LINE\"\n ],\n \"steps\": [\"layout/segmentation/line\"],\n \"parameters\": {\n \"overwrite_lines\": {\n \"type\": \"boolean\",\n \"default\": true,\n \"description\": \"remove existing layout and text annotation below the TextRegion level\"\n }\n }\n },\n \"ocrd-tesserocr-segment-word\": {\n \"executable\": \"ocrd-tesserocr-segment-word\",\n \"categories\": [\"Layout analysis\"],\n \"description\": \"Segment lines into words with tesseract\",\n \"input_file_grp\": [\n \"OCR-D-SEG-LINE\"\n ],\n \"output_file_grp\": [\n \"OCR-D-SEG-WORD\"\n ],\n \"steps\": [\"layout/segmentation/word\"],\n \"parameters\": {\n \"overwrite_words\": {\n \"type\": \"boolean\",\n \"default\": true,\n \"description\": \"remove existing layout and text annotation below the TextLine level\"\n }\n }\n },\n \"ocrd-tesserocr-crop\": {\n \"executable\": \"ocrd-tesserocr-crop\",\n \"categories\": [\"Image preprocessing\"],\n \"description\": \"Poor man's cropping with tesseract\",\n \"input_file_grp\": [\n\t\"OCR-D-IMG\"\n ],\n \"output_file_grp\": [\n\t\"OCR-D-IMG-CROPPED\"\n ],\n \"steps\": [\"preprocessing/optimization/cropping\"],\n \"parameters\" : {\n \"padding\": {\n \"type\": \"number\",\n \"format\": \"integer\",\n \"description\": \"extend detected border by this many (true) pixels on every side\",\n \"default\": 4\n }\n }\n },\n \"ocrd-tesserocr-binarize\": {\n \"executable\": \"ocrd-tesserocr-binarize\",\n \"categories\": [\"Image preprocessing\"],\n \"description\": \"Binarize regions or lines\",\n \"input_file_grp\": [\n \"OCR-D-IMG\",\n \"OCR-D-SEG-BLOCK\",\n \"OCR-D-SEG-LINE\"\n ],\n \"output_file_grp\": [\n \"OCR-D-BIN-BLOCK\",\n \"OCR-D-BIN-LINE\"\n ],\n \"steps\": [\"preprocessing/optimization/binarization\"],\n \"parameters\": {\n \"operation_level\": {\n \"type\": \"string\",\n \"enum\": [\"region\", \"line\"],\n \"default\": \"region\",\n \"description\": \"PAGE XML hierarchy level to operate on\"\n }\n }\n }\n }\n}\n",
+ "setup.py": "# -*- coding: utf-8 -*-\n\"\"\"\nInstalls five executables:\n\n - ocrd_tesserocr_recognize\n - ocrd_tesserocr_segment_region\n - ocrd_tesserocr_segment_line\n - ocrd_tesserocr_segment_word\n - ocrd_tesserocr_crop\n - ocrd_tesserocr_deskew\n - ocrd_tesserocr_binarize\n\"\"\"\nimport codecs\n\nfrom setuptools import setup, find_packages\n\nsetup(\n name='ocrd_tesserocr',\n version='0.4.0',\n description='Tesserocr bindings',\n long_description=codecs.open('README.rst', encoding='utf-8').read(),\n author='Konstantin Baierer, Kay-Michael W\u00fcrzner, Robert Sachunsky',\n author_email='unixprog@gmail.com, wuerzner@gmail.com, sachunsky@informatik.uni-leipzig.de',\n url='https://github.com/OCR-D/ocrd_tesserocr',\n license='Apache License 2.0',\n packages=find_packages(exclude=('tests', 'docs')),\n install_requires=open('requirements.txt').read().split('\\n'),\n package_data={\n '': ['*.json', '*.yml', '*.yaml'],\n },\n entry_points={\n 'console_scripts': [\n 'ocrd-tesserocr-recognize=ocrd_tesserocr.cli:ocrd_tesserocr_recognize',\n 'ocrd-tesserocr-segment-region=ocrd_tesserocr.cli:ocrd_tesserocr_segment_region',\n 'ocrd-tesserocr-segment-line=ocrd_tesserocr.cli:ocrd_tesserocr_segment_line',\n 'ocrd-tesserocr-segment-word=ocrd_tesserocr.cli:ocrd_tesserocr_segment_word',\n 'ocrd-tesserocr-crop=ocrd_tesserocr.cli:ocrd_tesserocr_crop',\n 'ocrd-tesserocr-deskew=ocrd_tesserocr.cli:ocrd_tesserocr_deskew',\n 'ocrd-tesserocr-binarize=ocrd_tesserocr.cli:ocrd_tesserocr_binarize',\n ]\n },\n)\n"
},
"git": {
- "last_commit": "Wed Aug 21 18:39:05 2019 +0200",
- "number_of_commits": "237"
+ "last_commit": "Mon Aug 26 05:16:59 2019 +0200",
+ "number_of_commits": "243"
},
"name": "ocrd_tesserocr",
"ocrd_tool": {
@@ -505,7 +523,7 @@
"categories": [
"Image preprocessing"
],
- "description": "Binarize pages, regions or lines",
+ "description": "Binarize regions or lines",
"executable": "ocrd-tesserocr-binarize",
"input_file_grp": [
"OCR-D-IMG",
@@ -710,8 +728,9 @@
]
}
},
- "version": "0.4.1"
+ "version": "0.3.0"
},
+ "ocrd_tool_validate": "<report valid=\"true\">\n</report>",
"org_plus_name": "OCR-D/ocrd_tesserocr",
"python": {
"author": "Konstantin Baierer, Kay-Michael W\u00fcrzner, Robert Sachunsky",
@@ -730,7 +749,7 @@
},
"git": {
"last_commit": "Thu Sep 26 17:20:39 2019 +0200",
- "number_of_commits": "1"
+ "number_of_commits": "71"
},
"name": "LAYoutERkennung",
"ocrd_tool": {
@@ -1259,6 +1278,7 @@
},
"version": "0.0.1"
},
+ "ocrd_tool_validate": "<report valid=\"false\">\n <error>[tools.ocrd-anybaseocr-tiseg.steps.0] 'layout/segmentation/text-image' is not one of ['preprocessing/characterization', 'preprocessing/optimization', 'preprocessing/optimization/cropping', 'preprocessing/optimization/deskewing', 'preprocessing/optimization/despeckling', 'preprocessing/optimization/dewarping', 'preprocessing/optimization/binarization', 'preprocessing/optimization/grayscale_normalization', 'recognition/text-recognition', 'recognition/font-identification', 'recognition/post-correction', 'layout/segmentation', 'layout/segmentation/text-nontext', 'layout/segmentation/region', 'layout/segmentation/line', 'layout/segmentation/word', 'layout/segmentation/classification', 'layout/analysis']</error>\n <error>[tools.ocrd-anybaseocr-layout-analysis.steps.0] 'layout/segmentation/text-image' is not one of ['preprocessing/characterization', 'preprocessing/optimization', 'preprocessing/optimization/cropping', 'preprocessing/optimization/deskewing', 'preprocessing/optimization/despeckling', 'preprocessing/optimization/dewarping', 'preprocessing/optimization/binarization', 'preprocessing/optimization/grayscale_normalization', 'recognition/text-recognition', 'recognition/font-identification', 'recognition/post-correction', 'layout/segmentation', 'layout/segmentation/text-nontext', 'layout/segmentation/region', 'layout/segmentation/line', 'layout/segmentation/word', 'layout/segmentation/classification', 'layout/analysis']</error>\n <error>[tools.ocrd-anybaseocr-block-segmentation.steps.0] 'layout/segmentation/text-image' is not one of ['preprocessing/characterization', 'preprocessing/optimization', 'preprocessing/optimization/cropping', 'preprocessing/optimization/deskewing', 'preprocessing/optimization/despeckling', 'preprocessing/optimization/dewarping', 'preprocessing/optimization/binarization', 'preprocessing/optimization/grayscale_normalization', 'recognition/text-recognition', 'recognition/font-identification', 'recognition/post-correction', 'layout/segmentation', 'layout/segmentation/text-nontext', 'layout/segmentation/region', 'layout/segmentation/line', 'layout/segmentation/word', 'layout/segmentation/classification', 'layout/analysis']</error>\n</report>",
"org_plus_name": "mjenckel/LAYoutERkennung",
"python": {
"author": "DFKI",
@@ -1277,10 +1297,11 @@
},
"git": {
"last_commit": "Fri Mar 29 16:48:09 2019 +0100",
- "number_of_commits": "1"
+ "number_of_commits": "3"
},
"name": "segmentation-runner",
- "ocrd_tool": null,
+ "ocrd_tool": "",
+ "ocrd_tool_validate": "NO ocrd-tool.json",
"org_plus_name": "ocr-d-modul-2-segmentierung/segmentation-runner",
"python": {
"author": "Alexander Gehrke, Christian Reul, Christoph Wick",
@@ -1302,7 +1323,8 @@
"number_of_commits": "1"
},
"name": "cor-asv-fst",
- "ocrd_tool": null,
+ "ocrd_tool": "",
+ "ocrd_tool_validate": "NO ocrd-tool.json",
"org_plus_name": "ASVLeipzig/cor-asv-fst",
"python": {
"author": "Maciej Sumalvico, Robert Sachunsky",
@@ -1324,7 +1346,8 @@
"number_of_commits": "1"
},
"name": "cor-asv-ann",
- "ocrd_tool": null,
+ "ocrd_tool": "",
+ "ocrd_tool_validate": "NO ocrd-tool.json",
"org_plus_name": "ASVLeipzig/cor-asv-ann",
"python": {
"author": "Robert Sachunsky",
@@ -1336,17 +1359,18 @@
},
{
"files": {
- "Dockerfile": null,
- "README.md": null,
+ "Dockerfile": "FROM ocrd/core\nMAINTAINER Florian Fink <finkf@cis.lmu.de>\nENV OCRD_VERSION \"ocrd-0.1\"\nENV PROFILER_GIT https://github.com/cisocrgroup/Profiler\nENV LC_ALL C.UTF-8\nENV LANG C.UTF-8\n\nVOLUME [\"/data\"]\n# update\nRUN apt-get update && \\\n apt-get install -y git cmake g++ libxerces-c-dev libcppunit-dev openjdk-8-jre\n\nENV VERSION \"2018-06-06\"\n# install profiler\nRUN mkdir /src && \\\n cd /src && \\\n git clone -b ocrd ${PROFILER_GIT} && \\\n cd Profiler && mkdir build && cd build && \\\n cmake -DCMAKE_BUILD_TYPE=release .. && \\\n make -j 4 profiler && \\\n mkdir /apps && \\\n cp bin/profiler /apps/ && \\\n cd / && \\\n\t\trm -rf /src/Profiler\nCOPY target/${OCRD_VERSION}-cli.jar /apps/\n\nENTRYPOINT [\"/bin/sh\", \"-c\"]\n#COPY target/${OCRD_VERSION}.war /usr/local/tomcat/webapps\n#COPY tomcat-users.xml ${CATALINA_HOME}/conf/tomcat-users.xml\n#COPY context.xml ${CATALINA_HOME}/webapps/manager/META-INF/context.xml\n#COPY context.xml ${CATALINA_HOME}/webapps/host-manager/META-INF/context.xml\n",
+ "README.md": "\nOCRD REST API\n====================\n\n\nEclipse/Maven project for OCRD Application Server REST API & UIF\n\n## prerequisites\n- JDK8 or better\n- Maven 3\n- Eclipse 4.X or better (installed maven plugin & e.g. Spring STS)\n\n\n## build, run & dev-steps\n\n### import to eclipse\n1. clone repo to your local machine\n2. Open Eclipse\n3. File->Import->Maven->existing Maven project\n4. Run from new projects's context menu Maven->Update project\n5. New Java code from RAML is generated in /target/generated-sources/raml-jaxrs\n\n\n### run local jetty dev-server\n\n#### steps:\n- run eclipse project on server: `RunLocalJetty.java`\n- Point your browser to http://localhost:8181\n * `/` shows html & js pages which reside in `src/webapp`\n * `/api/` points to all api endpoints\n\n\n#### API documentation:\n- install raml2html module (https://github.com/raml2html/raml2html)\n- to generate use: raml2html api.raml > api.html\n\n\n\nOCRD WEB APP\n====================\n\n- sources in webapp-src folder\n\n### contents\nall source files which are needed to build the webapp (e.g. backbone js code & HTML markup code)\n\n### build\nuse build scripts to create a build. The build-script shall sync the build to `src/webapp`\n",
"ocrd-tool.json": null,
"setup.py": null
},
"git": {
- "last_commit": "",
- "number_of_commits": ""
+ "last_commit": "Wed Jul 11 10:05:04 2018 +0200",
+ "number_of_commits": "1"
},
"name": "ocrd-postcorrection",
- "ocrd_tool": null,
+ "ocrd_tool": "",
+ "ocrd_tool_validate": "NO ocrd-tool.json",
"org_plus_name": "cisocrgroup/ocrd-postcorrection",
"python": {
"author": "",
@@ -1359,13 +1383,13 @@
{
"files": {
"Dockerfile": null,
- "README.md": "# ocrd_typegroups_classifier\n\n> Typegroups classifier for OCR\n\n## Quick setup\n\nIf needed, create a virtual environment for Python 3 (it was tested\nsuccessfully with Python 3.7), activate it, and install ocrd.\n\n```sh\nvirtualenv -p python3 ocrd-venv3\nsource ocrd-venv3/bin/activate\npip3 install ocrd\n```\n\nEnter in the folder containing the tool:\n```cd ocrd_typegroups_classifier/```\n\nInstall the module and its dependencies\n\n```\nmake install\nmake deps\n```\n\nFinally, run the test:\n\n```\nsh test/test.sh\n```\n\n** Important: ** The test makes sure that the system does work. For\nspeed reasons, a very small neural network is used and applied only to\nthe top-left corner of the image, therefore the quality of the results\nwill be of poor quality.\n\n## Models\n\nThe model classifier-1.tgc is based on a ResNet-18, with less neurons\nper layer than the usual model. It was briefly trained on 12 classes:\nAdornment, Antiqua, Bastarda, Book covers and other irrelevant data,\nEmpty Pages, Fraktur, Griechisch, Hebr\u00e4isch, Kursiv, Rotunda, Textura,\nand Woodcuts - Engravings.\n\n## Performance\n\nThe smaller the `stride`, the longer the runtime, the more accurate the\nresult are.\n\n\n",
+ "README.md": "# ocrd_typegroups_classifier\n\n> Typegroups classifier for OCR\n\n## Quick setup\n\nIf needed, create a virtual environment for Python 3 (it was tested\nsuccessfully with Python 3.7), activate it, and install ocrd.\n\n```sh\nvirtualenv -p python3 ocrd-venv3\nsource ocrd-venv3/bin/activate\npip3 install ocrd\n```\n\nEnter in the folder containing the tool:\n```cd ocrd_typegroups_classifier/```\n\nInstall the module and its dependencies\n\n```\nmake install\nmake deps\n```\n\nFinally, run the test:\n\n```\nsh test/test.sh\n```\n\n** Important: ** The test makes sure that the system does work. For\nspeed reasons, a very small neural network is used and applied only to\nthe top-left corner of the image, therefore the quality of the results\nwill be of poor quality.\n\n## Models\n\nThe model classifier-1.tgc is based on a ResNet-18, with less neurons\nper layer than the usual model. It was briefly trained on 12 classes:\nAdornment, Antiqua, Bastarda, Book covers and other irrelevant data,\nEmpty Pages, Fraktur, Griechisch, Hebr\u00e4isch, Kursiv, Rotunda, Textura,\nand Woodcuts - Engravings.\n\n## Heatmap Generation ##\nGiven a trained model, it is possible to produce heatmaps corresponding\nto classification results. Syntax:\n\n```\npython3 tools/heatmap.py ocrd_typegroups_classifier/models/classifier.tgc sample.jpg out\n```",
"ocrd-tool.json": "{\n \"version\": \"0.0.1\",\n \"git_url\": \"https://github.com/seuretm/ocrd_typegroups_classifier\",\n \"tools\": {\n \"ocrd-typegroups-classifier\": {\n \"executable\": \"ocrd-typegroups-classifier\",\n \"description\": \"Classification of 15th century type groups\",\n \"categories\": [\n \"Text recognition and optimization\"\n ],\n \"steps\": [\n \"recognition/font-identification\"\n ],\n \"parameters\": {\n \"network\": {\n \"description\": \"The file name of the neural network to use, including sufficient path information\",\n \"type\": \"string\",\n \"required\": true\n },\n \"stride\": {\n \"description\": \"Stride applied to the CNN on the image. Should be between 1 and 224. Smaller values increase the computation time.\",\n \"type\": \"number\",\n \"format\": \"integer\",\n \"default\": 112\n }\n }\n }\n }\n}\n",
"setup.py": "# -*- coding: utf-8 -*-\nimport codecs\n\nfrom setuptools import setup, find_packages\n\nwith codecs.open('README.md', encoding='utf-8') as f:\n README = f.read()\n\nsetup(\n name='ocrd_typegroups_classifier',\n version='0.0.1',\n description='Typegroups classifier for OCR',\n long_description=README,\n long_description_content_type='text/markdown',\n author='Matthias Seuret, Konstantin Baierer',\n author_email='seuretm@users.noreply.github.com',\n url='https://github.com/seuretm/ocrd_typegroups_classifier',\n license='Apache License 2.0',\n packages=find_packages(exclude=('tests', 'docs')),\n include_package_data=True,\n install_requires=[\n 'click',\n 'ocrd >= 1.0.0b7',\n 'pandas',\n 'Pillow >= 5.3.0',\n 'scikit-image',\n 'torch',\n 'torchvision',\n ],\n package_data={\n '': ['*.json', '*.tgc'],\n },\n entry_points={\n 'console_scripts': [\n 'typegroups-classifier=ocrd_typegroups_classifier.cli.simple:cli',\n 'ocrd-typegroups-classifier=ocrd_typegroups_classifier.cli.ocrd_cli:cli',\n ]\n },\n)\n"
},
"git": {
- "last_commit": "Sun Mar 24 18:35:45 2019 +0100",
- "number_of_commits": "33"
+ "last_commit": "Tue Apr 30 16:09:15 2019 +0200",
+ "number_of_commits": "47"
},
"name": "ocrd_typegroups_classifier",
"ocrd_tool": {
@@ -1397,6 +1421,7 @@
},
"version": "0.0.1"
},
+ "ocrd_tool_validate": "<report valid=\"false\">\n <error>[tools.ocrd-typegroups-classifier] 'input_file_grp' is a required property</error>\n <error>[tools.ocrd-typegroups-classifier] 'output_file_grp' is a required property</error>\n</report>",
"org_plus_name": "seuretm/ocrd_typegroups_classifier",
"python": {
"author": "Matthias Seuret, Konstantin Baierer",
@@ -1414,8 +1439,8 @@
"setup.py": "from io import open\nfrom setuptools import find_packages, setup\n\nwith open('requirements.txt') as fp:\n install_requires = fp.read()\n\nsetup(\n name='dinglehopper',\n author='Mike Gerber, The QURATOR SPK Team',\n author_email='mike.gerber@sbb.spk-berlin.de, qurator@sbb.spk-berlin.de',\n description='The OCR evaluation tool',\n long_description=open('README.md', 'r', encoding='utf-8').read(),\n long_description_content_type='text/markdown',\n keywords='qurator ocr',\n license='Apache',\n namespace_packages=['qurator'],\n packages=find_packages(exclude=['*.tests', '*.tests.*', 'tests.*', 'tests']),\n install_requires=install_requires,\n package_data={\n '': ['*.json', 'templates/*'],\n },\n entry_points={\n 'console_scripts': [\n 'dinglehopper=qurator.dinglehopper.cli:main',\n 'ocrd-dinglehopper=qurator.dinglehopper.ocrd_cli:ocrd_dinglehopper',\n ]\n }\n)\n"
},
"git": {
- "last_commit": "Fri Oct 18 16:38:44 2019 +0200",
- "number_of_commits": "2"
+ "last_commit": "Fri Oct 18 17:45:24 2019 +0200",
+ "number_of_commits": "1"
},
"name": "dinglehopper",
"ocrd_tool": {
@@ -1440,6 +1465,7 @@
}
}
},
+ "ocrd_tool_validate": "<report valid=\"false\">\n <error>[] 'version' is a required property</error>\n</report>",
"org_plus_name": "qurator-spk/dinglehopper",
"python": {
"author": "Mike Gerber, The QURATOR SPK Team",
--
GitLab