Commit 3484f3bf authored by Alexander Gehrke's avatar Alexander Gehrke

Split out frontend code to separate module

parents
[bumpversion]
current_version = 0.3.0
commit = True
tag = True
[bumpversion:file:setup.py]
# Byte-compiled / optimized / DLL files
__pycache__/
*.py[cod]
*$py.class
# C extensions
*.so
# Distribution / packaging
.Python
build/
develop-eggs/
dist/
downloads/
eggs/
.eggs/
lib64/
parts/
sdist/
var/
wheels/
*.egg-info/
.installed.cfg
*.egg
MANIFEST
# PyInstaller
# Usually these files are written by a python script from a template
# before PyInstaller builds the exe, so as to inject date/other infos into it.
*.manifest
*.spec
# Installer logs
pip-log.txt
pip-delete-this-directory.txt
# Unit test / coverage reports
htmlcov/
.tox/
.coverage
.coverage.*
.cache
nosetests.xml
coverage.xml
*.cover
.hypothesis/
.pytest_cache/
# Translations
*.mo
*.pot
# Django stuff:
*.log
.static_storage/
.media/
local_settings.py
# Flask stuff:
instance/
.webassets-cache
# Scrapy stuff:
.scrapy
# Sphinx documentation
docs/_build/
# PyBuilder
target/
# Jupyter Notebook
.ipynb_checkpoints
# pyenv
.python-version
# celery beat schedule file
celerybeat-schedule
# SageMath parsed files
*.sage.py
# Environments
.env
.venv
env/
venv/
ENV/
env.bak/
venv.bak/
# Spyder project settings
.spyderproject
.spyproject
# Rope project settings
.ropeproject
# mkdocs documentation
/site
# mypy
.mypy_cache/
# Vim
*~
# PyCharm
.idea
Apache-2.0 OR GPL-3.0-or-later
Apache License
Version 2.0, January 2004
http://www.apache.org/licenses/
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
1. Definitions.
"License" shall mean the terms and conditions for use, reproduction,
and distribution as defined by Sections 1 through 9 of this document.
"Licensor" shall mean the copyright owner or entity authorized by
the copyright owner that is granting the License.
"Legal Entity" shall mean the union of the acting entity and all
other entities that control, are controlled by, or are under common
control with that entity. For the purposes of this definition,
"control" means (i) the power, direct or indirect, to cause the
direction or management of such entity, whether by contract or
otherwise, or (ii) ownership of fifty percent (50%) or more of the
outstanding shares, or (iii) beneficial ownership of such entity.
"You" (or "Your") shall mean an individual or Legal Entity
exercising permissions granted by this License.
"Source" form shall mean the preferred form for making modifications,
including but not limited to software source code, documentation
source, and configuration files.
"Object" form shall mean any form resulting from mechanical
transformation or translation of a Source form, including but
not limited to compiled object code, generated documentation,
and conversions to other media types.
"Work" shall mean the work of authorship, whether in Source or
Object form, made available under the License, as indicated by a
copyright notice that is included in or attached to the work
(an example is provided in the Appendix below).
"Derivative Works" shall mean any work, whether in Source or Object
form, that is based on (or derived from) the Work and for which the
editorial revisions, annotations, elaborations, or other modifications
represent, as a whole, an original work of authorship. For the purposes
of this License, Derivative Works shall not include works that remain
separable from, or merely link (or bind by name) to the interfaces of,
the Work and Derivative Works thereof.
"Contribution" shall mean any work of authorship, including
the original version of the Work and any modifications or additions
to that Work or Derivative Works thereof, that is intentionally
submitted to Licensor for inclusion in the Work by the copyright owner
or by an individual or Legal Entity authorized to submit on behalf of
the copyright owner. For the purposes of this definition, "submitted"
means any form of electronic, verbal, or written communication sent
to the Licensor or its representatives, including but not limited to
communication on electronic mailing lists, source code control systems,
and issue tracking systems that are managed by, or on behalf of, the
Licensor for the purpose of discussing and improving the Work, but
excluding communication that is conspicuously marked or otherwise
designated in writing by the copyright owner as "Not a Contribution."
"Contributor" shall mean Licensor and any individual or Legal Entity
on behalf of whom a Contribution has been received by Licensor and
subsequently incorporated within the Work.
2. Grant of Copyright License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
copyright license to reproduce, prepare Derivative Works of,
publicly display, publicly perform, sublicense, and distribute the
Work and such Derivative Works in Source or Object form.
3. Grant of Patent License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
(except as stated in this section) patent license to make, have made,
use, offer to sell, sell, import, and otherwise transfer the Work,
where such license applies only to those patent claims licensable
by such Contributor that are necessarily infringed by their
Contribution(s) alone or by combination of their Contribution(s)
with the Work to which such Contribution(s) was submitted. If You
institute patent litigation against any entity (including a
cross-claim or counterclaim in a lawsuit) alleging that the Work
or a Contribution incorporated within the Work constitutes direct
or contributory patent infringement, then any patent licenses
granted to You under this License for that Work shall terminate
as of the date such litigation is filed.
4. Redistribution. You may reproduce and distribute copies of the
Work or Derivative Works thereof in any medium, with or without
modifications, and in Source or Object form, provided that You
meet the following conditions:
(a) You must give any other recipients of the Work or
Derivative Works a copy of this License; and
(b) You must cause any modified files to carry prominent notices
stating that You changed the files; and
(c) You must retain, in the Source form of any Derivative Works
that You distribute, all copyright, patent, trademark, and
attribution notices from the Source form of the Work,
excluding those notices that do not pertain to any part of
the Derivative Works; and
(d) If the Work includes a "NOTICE" text file as part of its
distribution, then any Derivative Works that You distribute must
include a readable copy of the attribution notices contained
within such NOTICE file, excluding those notices that do not
pertain to any part of the Derivative Works, in at least one
of the following places: within a NOTICE text file distributed
as part of the Derivative Works; within the Source form or
documentation, if provided along with the Derivative Works; or,
within a display generated by the Derivative Works, if and
wherever such third-party notices normally appear. The contents
of the NOTICE file are for informational purposes only and
do not modify the License. You may add Your own attribution
notices within Derivative Works that You distribute, alongside
or as an addendum to the NOTICE text from the Work, provided
that such additional attribution notices cannot be construed
as modifying the License.
You may add Your own copyright statement to Your modifications and
may provide additional or different license terms and conditions
for use, reproduction, or distribution of Your modifications, or
for any such Derivative Works as a whole, provided Your use,
reproduction, and distribution of the Work otherwise complies with
the conditions stated in this License.
5. Submission of Contributions. Unless You explicitly state otherwise,
any Contribution intentionally submitted for inclusion in the Work
by You to the Licensor shall be under the terms and conditions of
this License, without any additional terms or conditions.
Notwithstanding the above, nothing herein shall supersede or modify
the terms of any separate license agreement you may have executed
with Licensor regarding such Contributions.
6. Trademarks. This License does not grant permission to use the trade
names, trademarks, service marks, or product names of the Licensor,
except as required for reasonable and customary use in describing the
origin of the Work and reproducing the content of the NOTICE file.
7. Disclaimer of Warranty. Unless required by applicable law or
agreed to in writing, Licensor provides the Work (and each
Contributor provides its Contributions) on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
implied, including, without limitation, any warranties or conditions
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
PARTICULAR PURPOSE. You are solely responsible for determining the
appropriateness of using or redistributing the Work and assume any
risks associated with Your exercise of permissions under this License.
8. Limitation of Liability. In no event and under no legal theory,
whether in tort (including negligence), contract, or otherwise,
unless required by applicable law (such as deliberate and grossly
negligent acts) or agreed to in writing, shall any Contributor be
liable to You for damages, including any direct, indirect, special,
incidental, or consequential damages of any character arising as a
result of this License or out of the use or inability to use the
Work (including but not limited to damages for loss of goodwill,
work stoppage, computer failure or malfunction, or any and all
other commercial damages or losses), even if such Contributor
has been advised of the possibility of such damages.
9. Accepting Warranty or Additional Liability. While redistributing
the Work or Derivative Works thereof, You may choose to offer,
and charge a fee for, acceptance of support, warranty, indemnity,
or other liability obligations and/or rights consistent with this
License. However, in accepting such obligations, You may act only
on Your own behalf and on Your sole responsibility, not on behalf
of any other Contributor, and only if You agree to indemnify,
defend, and hold each Contributor harmless for any liability
incurred by, or claims asserted against, such Contributor by reason
of your accepting any such warranty or additional liability.
END OF TERMS AND CONDITIONS
APPENDIX: How to apply the Apache License to your work.
To apply the Apache License to your work, attach the following
boilerplate notice, with the fields enclosed by brackets "[]"
replaced with your own identifying information. (Don't include
the brackets!) The text should be enclosed in the appropriate
comment syntax for the file format. We also recommend that a
file or class name and description of purpose be included on the
same "printed page" as the copyright notice for easier
identification within third-party archives.
Copyright [yyyy] [name of copyright owner]
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.
This diff is collapsed.
# OCR4All Pixel Classifier
## Requirements
Python dependencies are specified in `requirements.txt` / `setup.py`.
You must install the package via pip with either `ocr4all_pixel_classifier[tf_cpu]` to
use CPU version of tensorflow or `ocr4all_pixel_classifier[tf_gpu]` to use GPU (CUDA)
version of tensorflow. For the latter, your system should be set up with CUDA 9
and CuDNN 7.
## Usage
### Pixel classifier
#### Classification
To run a model on some input images, use `ocr4all-pixel-classifier predict`:
```sh
ocr4all-pixel-classifier predict --load PATH_TO_MODEL \
--output OUTPUT_PATH \
--binary PATH_TO_BINARY_IMAGES \
--images PATH_TO_SOURCE_IMAGES \
--norm PATH_TO_NORMALIZATIONS
```
(`ocr4all-pixel-classifier` is an alias for `ocr4all-pixel-classifier predict`)
This will create three folders at the output path:
- `color`: the classification as color image, with pixel color corresponding to
the class for that pixel
- `inverted`: inverted binary image with classification of foreground pixels
only (i.e. background is black, foreground is white or class color)
- `overlay`: classification image layered transparently over the original image
#### Training
For training, you first have to create dataset files. A dataset file is a JSON
file containing three arrays, for train, test and evaluation data (also
called train/validation/test in other publications). The JSON file uses the
following format:
```json
{
"train": [
//datasets here
],
"test": [
//datasets here
],
"eval": [
//datasets here
]
}
```
A dataset describes a single input image and consists of several paths: the
original image, a binarized version and the mask (pixel color corresponds to
class). Furthermore, the line height of the page in pixels must be specified:
```json
{
"binary_path": "/path/to/image/binary/filename.bin.png",
"image_path": "/path/to/image/color/filename.jpg",
"mask_path": "/path/to/image/mask/filename_MASK.png",
"line_height_px": 18
}
```
The generation of dataset files can be automated using `ocr4all-pixel-classifier
create-dataset-file`. Refer to the command's `--help` output for further
information.
To start the training:
```sh
ocr4all-pixel-classifier train \
--train DATASET_FILE.json --test DATASET_FILE.json --eval DATASET_FILE.json \
--output MODEL_TARGET_PATH \
--n_iter 5000
```
The parameters `--train`, `--test` and `--eval` may be followed by any number of
dataset files or patterns (shell globbing).
Refer to `ocr4all-pixel-classifier train --help` for further parameters provided to
affect the training procedure.
You can combine several dataset files into a _split file_. The format of the
split file is:
```json
{
"label": "name of split",
"train": [
"/path/to/dataset1.json",
"/path/to/dataset2.json",
...
],
"test": [
//dataset paths here
],
"eval": [
//dataset paths here
]
}
```
To use a split file, add the `--split_file` parameter.
### Examples
See the examples for [dataset generation](examples/dataset-creation-example.sh) and [training](examples/model-training-example.sh)
### `ocr4all-pixel-classifier compute-image-normalizations` / `ocrd_compute_normalizations`
Calculate image normalizations, i.e. scaling factors based on average line
height.
Required arguments:
- `--input_dir`: location of images
- `--output_dir`: target location of norm files
Optional arguments:
- `--average_all`: Average height over all images
- `--inverse`
#!/bin/sh
# Example of creating a dataset for ocr4all-pixel-classifier
#
# This assumes your folder structure looks like this:
# base dir
# ├── book1
# │   ├── binary <- Binarized version of image
# │   ├── jpg <- Color version of image
# │   └── page <- PageXML
# ├── ...
# └── bookN
# ├── binary
# ├── jpg
# └── page
for book in book*; do
# Generate the masks for training
# --setting defines, which region types will be used:
# - all_types: one color for each region type in PageXML
# - text_nontext: red for text, green for non_text
# - baseline: draw baselines of text lines
# - textline: draw polygons of text lines
# we set --image_map_dir to the current directory, which will overwrite the
# output in each loop, but the image map generated is constant for each
# setting and only one file is needed for training
ocr4all-pixel-classifier gen-masks \
--input-dir $book/page \
--output-dir $book/masks \
--threads $(nproc) \
--setting text_nontext \
--image-map_dir ./
# Estimate the xheight for all pages based on connected components in binary
# image.
# When running on images with different dpi/fontsize, don't use --average_all
ocr4all-pixel-classifier compute-image-normalizations \
--input-dir $book/binary
--average-all \
--output-dir $book/norms
# create a json file usable as input for the pixel classifier's train command
# --n_train and --n_test determine the size of the training and validation set
# (note that validation set is called test set in the pixel classifier for
# historical reasons)
ocr4all-pixel-classifier create-dataset-file \
--images-dir jpg \
--binary-dir binary \
--masks-dir masks \
--normalizations-dir norms \
--output-file $book/dataset.json \
--n-train 0.8 --n-test 0.2
--dataset-path $(realpath $book/)
done
# Example call for training a model
# This trains a model based on the data in the given json files (see
# dataset-creation-example.sh)
#
# Note that the dataset files already differentiate between train,
# test/validation and evaluation dataset, so even if you specify datasets for
# both train and test, only the image in the relevant section in the JSON will
# be used for each group
#
# --n-epoch / -E specifies the number of epochs for training, i.e. the training
# duration. We also specify the number of iterations a worse performance is
# allowed, when the model does not improve for that long the training stops
# (only possible with test dataset). Of course we keep the best model, not the
# one after the performance drops.
#
# --output specifies the folder where model.h5 and and logs will be placed.
ocr4all-pixel-classifier train \
--train dataset1.json dataset2.json dataset3.json \
--test dataset1.json dataset2.json dataset3.json \
--n-epoch 100 \
--early-stopping-max-performance-drops 30 \
--output my-model \
--color_map image_map.json
# if using a split file:
ocr4all-pixel-classifier train \
--split-file splits.json \
-E 100 \
-S 30 \
--output my-model \
--color_map image_map.json
# you can also use --load to specify an existing model on which to continue
# training. There are some minor tuning options available, see the help output
# for the "train" command for those:
ocr4all-pixel-classifier train --help
import argparse
import json
import multiprocessing
import os
import sys
from functools import partial
from math import isnan
import numpy as np
import tqdm
from ocr4all_pixel_classifier.lib.image_ops import compute_char_height
def compute_normalizations(input_dir, output_dir=None, inverse=False, average_all=True):
if not os.path.exists(input_dir):
raise Exception("Cannot open {}".format(input_dir))
if not os.path.isdir(input_dir):
files = [input_dir]
else:
files = [os.path.join(input_dir, f) for f in os.listdir(input_dir)]
# files = files[:10]
with multiprocessing.Pool(processes=12) as p:
char_heights = [v for v in
tqdm.tqdm(p.imap(partial(compute_char_height, inverse=inverse), files), total=len(files))
]
av_height = np.mean([c for c in char_heights if c])
if isnan(av_height):
raise Exception("No chars found in dataset")
if average_all:
char_heights = [av_height] * len(char_heights)
if output_dir:
os.makedirs(output_dir, exist_ok=True)
for file, height in zip(files, char_heights):
filename, file_extension = os.path.splitext(os.path.basename(file))
if height is None:
height = av_height
if output_dir:
output_file = os.path.join(output_dir, filename + ".norm")
with open(output_file, 'w') as f:
json.dump(
{"file": file, "char_height": int(height)},
f,
indent=4
)
def main():
parser = argparse.ArgumentParser(add_help=False)
paths_args = parser.add_argument_group("Paths")
paths_args.add_argument("-I", "--input-dir", type=str, required=True,
help="Image directory to process")
paths_args.add_argument("-O", "--output-dir", type=str, required=True,
help="The output dir for the normalization data")
opt_args = parser.add_argument_group("optional arguments")
opt_args.add_argument("-h", "--help", action="help", help="show this help message and exit")
opt_args.add_argument("--average-all", "--average_all", action="store_true",
help="Use average height over all images.")
opt_args.add_argument("--inverse", action="store_true",
help="use if white is foreground")
opt_args.add_argument("--debug", action="store_true")
args = parser.parse_args()
if args.debug:
compute_normalizations(args.input_dir, args.output_dir, args.inverse, args.average_all)
else:
try:
import warnings
warnings.filterwarnings('ignore')
compute_normalizations(args.input_dir, args.output_dir, args.inverse, args.average_all)
except Exception:
print("Error:", sys.exc_info()[1])
if __name__ == '__main__':
main()
import argparse
from ocr4all_pixel_classifier.lib.dataset import list_dataset, single_split, create_splits
from random import seed
import json
def main():
parser = argparse.ArgumentParser(add_help=False)
paths_args = parser.add_argument_group("Main paths")
paths_args.add_argument("-D", "--dataset-path", type=str, required=True,
help="base path of dataset")
paths_args.add_argument("-O", "--output-file", type=str, required=True,
help="output location for dataset JSON. for generating multiple splits, add {} where the number should be.")