Commit 59c6ff66 authored by Jonas Müller's avatar Jonas Müller

init

parents
# Data dir
data/imgs/
# Byte-compiled / optimized / DLL files
__pycache__/
*.py[cod]
*$py.class
# C extensions
*.so
# Distribution / packaging
.Python
env/
build/
develop-eggs/
dist/
downloads/
eggs/
.eggs/
lib/
lib64/
parts/
sdist/
var/
*.egg-info/
.installed.cfg
*.egg
# PyInstaller
# Usually these files are written by a python script from a template
# before PyInstaller builds the exe, so as to inject date/other infos into it.
*.manifest
*.spec
# Installer logs
pip-log.txt
pip-delete-this-directory.txt
# Unit test / coverage reports
htmlcov/
.tox/
.coverage
.coverage.*
.cache
nosetests.xml
coverage.xml
*,cover
.hypothesis/
# Translations
*.mo
*.pot
# Django stuff:
*.log
local_settings.py
# Flask stuff:
instance/
.webassets-cache
# Scrapy stuff:
.scrapy
# Sphinx documentation
docs/_build/
# PyBuilder
target/
# IPython Notebook
.ipynb_checkpoints
# pyenv
.python-version
# celery beat schedule file
celerybeat-schedule
# dotenv
.env
# virtualenv
venv/
ENV/
# Spyder project settings
.spyderproject
# Rope project settings
.ropeproject
# hdf5
*.h5
*.hdf5
File added
# Default ignored files
/workspace.xml
\ No newline at end of file
<component name="InspectionProjectProfileManager">
<settings>
<option name="USE_PROJECT_PROFILE" value="false" />
<version value="1.0" />
</settings>
</component>
\ No newline at end of file
<?xml version="1.0" encoding="UTF-8"?>
<module type="PYTHON_MODULE" version="4">
<component name="NewModuleRootManager">
<content url="file://$MODULE_DIR$" />
<orderEntry type="jdk" jdkName="Remote Python 3.6.9 Docker (diofor/tensorflow:no_gpu)" jdkType="Python SDK" />
<orderEntry type="sourceFolder" forTests="false" />
</component>
<component name="PyDocumentationSettings">
<option name="format" value="PLAIN" />
<option name="myDocStringFormat" value="Plain" />
</component>
</module>
\ No newline at end of file
<?xml version="1.0" encoding="UTF-8"?>
<project version="4">
<component name="JavaScriptSettings">
<option name="languageLevel" value="ES6" />
</component>
<component name="ProjectRootManager" version="2" project-jdk-name="Remote Python 3.6.9 Docker (diofor/tensorflow:no_gpu)" project-jdk-type="Python SDK" />
<component name="PythonCompatibilityInspectionAdvertiser">
<option name="version" value="3" />
</component>
</project>
\ No newline at end of file
<?xml version="1.0" encoding="UTF-8"?>
<project version="4">
<component name="ProjectModuleManager">
<modules>
<module fileurl="file://$PROJECT_DIR$/.idea/keras-frcnn-master.iml" filepath="$PROJECT_DIR$/.idea/keras-frcnn-master.iml" />
</modules>
</component>
</project>
\ No newline at end of file
<?xml version="1.0" encoding="UTF-8"?>
<project version="4">
<component name="PySciProjectComponent">
<option name="PY_SCI_VIEW_SUGGESTED" value="true" />
</component>
</project>
\ No newline at end of file
<?xml version="1.0" encoding="UTF-8"?>
<project version="4">
<component name="VcsDirectoryMappings">
<mapping directory="$PROJECT_DIR$" vcs="Git" />
</component>
</project>
\ No newline at end of file
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.
# keras-frcnn
Keras implementation of Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks.
cloned from https://github.com/yhenon/keras-frcnn/
Please note that I currently am quite busy with other projects and unfortunately dont have a lot of time to spend on this maintaining this repository, but any contributions are welcome!
USAGE:
- Both theano and tensorflow backends are supported. However compile times are very high in theano, and tensorflow is highly recommended.
- `train_frcnn.py` can be used to train a model. To train on Pascal VOC data, simply do:
`python train_frcnn.py -p /path/to/pascalvoc/`.
- the Pascal VOC data set (images and annotations for bounding boxes around the classified objects) can be obtained from: http://host.robots.ox.ac.uk/pascal/VOC/voc2012/VOCtrainval_11-May-2012.tar
- simple_parser.py provides an alternative way to input data, using a text file. Simply provide a text file, with each
line containing:
`filepath,x1,y1,x2,y2,class_name`
For example:
/data/imgs/img_001.jpg,837,346,981,456,cow
/data/imgs/img_002.jpg,215,312,279,391,cat
The classes will be inferred from the file. To use the simple parser instead of the default pascal voc style parser,
use the command line option `-o simple`. For example `python train_frcnn.py -o simple -p my_data.txt`.
- Running `train_frcnn.py` will write weights to disk to an hdf5 file, as well as all the setting of the training run to a `pickle` file. These
settings can then be loaded by `test_frcnn.py` for any testing.
- test_frcnn.py can be used to perform inference, given pretrained weights and a config file. Specify a path to the folder containing
images:
`python test_frcnn.py -p /path/to/test_data/`
- Data augmentation can be applied by specifying `--hf` for horizontal flips, `--vf` for vertical flips and `--rot` for 90 degree rotations
NOTES:
- config.py contains all settings for the train or test run. The default settings match those in the original Faster-RCNN
paper. The anchor box sizes are [128, 256, 512] and the ratios are [1:1, 1:2, 2:1].
- The theano backend by default uses a 7x7 pooling region, instead of 14x14 as in the frcnn paper. This cuts down compiling time slightly.
- The tensorflow backend performs a resize on the pooling region, instead of max pooling. This is much more efficient and has little impact on results.
Example output:
![ex1](http://i.imgur.com/7Lmb2RC.png)
![ex2](http://i.imgur.com/h58kCIV.png)
![ex3](http://i.imgur.com/EbvGBaG.png)
![ex4](http://i.imgur.com/i5UAgLb.png)
ISSUES:
- If you get this error:
`ValueError: There is a negative shape in the graph!`
than update keras to the newest version
- This repo was developed using `python2`. `python3` should work thanks to the contribution of a number of users.
- If you run out of memory, try reducing the number of ROIs that are processed simultaneously. Try passing a lower `-n` to `train_frcnn.py`. Alternatively, try reducing the image size from the default value of 600 (this setting is found in `config.py`.
File added
This diff is collapsed.
This source diff could not be displayed because it is too large. You can view the blob instead.
from random import shuffle
from math import ceil
from PIL import Image
import json
import io
import os
import tensorflow as tf
DEBUG = False
annotation_file = "caries_dataset_annotation.json"
out_file = 'annotations.txt'
img_path = 'imgs/'
dictionary = {}
def get_filenames_list_and_dict():
caries = []
no_caries = []
print(os.getcwd())
with open(annotation_file) as file:
json_data = json.load(file)
for picture in json_data:
current_name = picture['External ID']
if not os.path.isfile(img_path+current_name):
print('File ”{}” not found. Therefore it\'s not part of the record file.'.format(current_name))
continue
if 'CARIES' in picture['Label']:
caries.append(current_name)
dictionary[current_name] = picture['Label']['CARIES']
else:
no_caries.append(current_name)
return caries, no_caries
def print_information(caries, no_caries):
print('Caries', len(filenames_caries))
print(caries[:5])
print()
print('No Caries', len(filenames_no_caries))
print(no_caries[:5])
def get_caries_entries_as_list(filename):
entries = []
if filename in dictionary.keys():
for bbox in dictionary[filename]:
if DEBUG: print(bbox)
x, y = [], []
for point in bbox['geometry']:
x.append(point['x'])
y.append(point['y'])
if DEBUG: print(min(x), max(x), min(y), max(y))
if DEBUG: print()
entries.append('data/'+img_path+filename+','+str(min(x))+','+str(min(y))+','+str(max(x))+','+str(max(y))+','+'caries\n')
return entries
if __name__ == '__main__':
filenames_caries, filenames_no_caries = get_filenames_list_and_dict()
# reduce amount of data only for testing purpose
# remove for real use
#filenames_caries = filenames_caries[:len(filenames_no_caries)]
print_information(filenames_caries, filenames_no_caries)
shuffle(filenames_caries)
shuffle(filenames_no_caries)
test = 0.2 # quota of test examples from the whole dataset.
caries_splitting_element = ceil(len(filenames_caries) * test)
no_caries_splitting_element = ceil(len(filenames_no_caries) * test)
print(caries_splitting_element)
print(no_caries_splitting_element)
filenames = {}
filenames['test'] = filenames_caries[:caries_splitting_element]
filenames['test'].extend(filenames_no_caries[:no_caries_splitting_element])
filenames['train'] = filenames_caries[caries_splitting_element:]
filenames['train'].extend(filenames_no_caries[no_caries_splitting_element:])
'''for kind in filenames.keys():
writer = tf.io.TFRecordWriter('../data/'+kind +'.record')
for filename in filenames[kind]:
tf_example = create_tf_example(filename)
writer.write(tf_example.SerializeToString())
writer.close()
print('Successfully created the ' + kind + ' TFRecords')'''
with open(out_file, 'w') as file:
for filename in filenames['train']:
file.writelines(get_caries_entries_as_list(filename))
import os
test_path = 'imgs/train_only_annotated/'
annotation_file = 'annotations.txt'
def removeImage(filename):
if os.path.isfile(test_path+filename):
os.remove(test_path+filename)
print("File {} removed.".format(filename))
else:
print("File {} does not exist.".format(filename))
def load_names_of_train_images():
filenames = set()
with open(annotation_file) as file:
for line in file.readlines():
filenames.add(line.split(',')[0].split('/')[-1])
return list(filenames)
if __name__ == '__main__':
filenames = load_names_of_train_images()
for idx, img_name in enumerate(sorted(os.listdir(test_path))):
if not img_name.lower().endswith(('.bmp', '.jpeg', '.jpg', '.png', '.tif', '.tiff')):
continue
if not img_name in filenames:
removeImage(img_name)
import os
test_path = 'imgs/test/'
annotation_file = 'annotations.txt'
def removeImage(filename):
if os.path.isfile(test_path+filename):
os.remove(test_path+filename)
print("File {} removed.".format(filename))
else:
print("File {} does not exist.".format(filename))
def load_names_of_train_images():
filenames = set()
with open(annotation_file) as file:
for line in file.readlines():
filenames.add(line.split(',')[0].split('/')[-1])
return list(filenames)
if __name__ == '__main__':
filenames = load_names_of_train_images()
for training_image in filenames:
removeImage(training_image)
\ No newline at end of file
filenames_caries
\ No newline at end of file
from keras.engine import Layer, InputSpec
from keras import initializers, regularizers
from keras import backend as K
class FixedBatchNormalization(Layer):
def __init__(self, epsilon=1e-3, axis=-1,
weights=None, beta_init='zero', gamma_init='one',
gamma_regularizer=None, beta_regularizer=None, **kwargs):
self.supports_masking = True
self.beta_init = initializers.get(beta_init)
self.gamma_init = initializers.get(gamma_init)
self.epsilon = epsilon
self.axis = axis
self.gamma_regularizer = regularizers.get(gamma_regularizer)
self.beta_regularizer = regularizers.get(beta_regularizer)
self.initial_weights = weights
super(FixedBatchNormalization, self).__init__(**kwargs)
def build(self, input_shape):
self.input_spec = [InputSpec(shape=input_shape)]
shape = (input_shape[self.axis],)
self.gamma = self.add_weight(shape,
initializer=self.gamma_init,
regularizer=self.gamma_regularizer,
name='{}_gamma'.format(self.name),
trainable=False)
self.beta = self.add_weight(shape,
initializer=self.beta_init,
regularizer=self.beta_regularizer,
name='{}_beta'.format(self.name),
trainable=False)
self.running_mean = self.add_weight(shape, initializer='zero',
name='{}_running_mean'.format(self.name),
trainable=False)
self.running_std = self.add_weight(shape, initializer='one',
name='{}_running_std'.format(self.name),
trainable=False)
if self.initial_weights is not None:
self.set_weights(self.initial_weights)
del self.initial_weights
self.built = True
def call(self, x, mask=None</