https://github.com/broadinstitute/keras-rcnn

Keras package for region-based convolutional neural networks (RCNNs)
https://github.com/broadinstitute/keras-rcnn

cntk deep-learning image-segmentation object-detection tensorflow theano

Last synced: 1 day ago
JSON representation

Keras package for region-based convolutional neural networks (RCNNs)

• Host: GitHub
• URL: https://github.com/broadinstitute/keras-rcnn
• Owner: broadinstitute
• License: other
• Created: 2017-04-25T13:32:06.000Z (over 7 years ago)
• Default Branch: master
• Last Pushed: 2020-05-20T00:44:02.000Z (over 4 years ago)
• Last Synced: 2025-01-15T00:11:27.548Z (8 days ago)
• Topics: cntk, deep-learning, image-segmentation, object-detection, tensorflow, theano
• Language: Python
• Homepage:
• Size: 5.07 MB
• Stars: 555
• Watchers: 39
• Forks: 221
• Open Issues: 71
• Metadata Files:
  • Readme: README.rst
  • License: LICENSE

Awesome Lists containing this project

README

        
Keras-RCNN

==========

.. image:: https://travis-ci.org/broadinstitute/keras-rcnn.svg?branch=master

    :target: https://travis-ci.org/broadinstitute/keras-rcnn

.. image:: https://codecov.io/gh/broadinstitute/keras-rcnn/branch/master/graph/badge.svg

    :target: https://codecov.io/gh/broadinstitute/keras-rcnn

keras-rcnn is *the* Keras package for region-based convolutional

neural networks.

Requirements

---------------

Python 3

keras-resnet==0.2.0

numpy==1.16.2

tensorflow==1.13.1

Keras==2.2.4

scikit-image==0.15.0

Getting Started

---------------

Let’s read and inspect some data:

.. code:: python

    training_dictionary, test_dictionary = keras_rcnn.datasets.shape.load_data()

    categories = {"circle": 1, "rectangle": 2, "triangle": 3}

    generator = keras_rcnn.preprocessing.ObjectDetectionGenerator()

    generator = generator.flow_from_dictionary(

        dictionary=training_dictionary,

        categories=categories,

        target_size=(224, 224)

    )

    validation_data = keras_rcnn.preprocessing.ObjectDetectionGenerator()

    validation_data = validation_data.flow_from_dictionary(

        dictionary=test_dictionary,

        categories=categories,

        target_size=(224, 224)

    )

    target, _ = generator.next()

    

    target_bounding_boxes, target_categories, target_images, target_masks, target_metadata = target

    target_bounding_boxes = numpy.squeeze(target_bounding_boxes)

    target_images = numpy.squeeze(target_images)

    target_categories = numpy.argmax(target_categories, -1)

    target_categories = numpy.squeeze(target_categories)

    keras_rcnn.utils.show_bounding_boxes(target_images, target_bounding_boxes, target_categories)

Let’s create an RCNN instance:

.. code:: python

    model = keras_rcnn.models.RCNN((224, 224, 3), ["circle", "rectangle", "triangle"])

and pass our preferred optimizer to the `compile` method:

.. code:: python

    optimizer = keras.optimizers.Adam(0.0001)

    model.compile(optimizer)

Finally, let’s use the `fit_generator` method to train our network:

.. code:: python

    model.fit_generator(    

        epochs=10,

        generator=generator,

        validation_data=validation_data

    )

External Data

-------------

The data is made up of a list of dictionaries corresponding to images. 

* For each image, add a dictionary with keys 'image', 'objects'

    * 'image' is a dictionary, which contains keys 'checksum', 'pathname', and 'shape'

        * 'checksum' is the md5 checksum of the image

        * 'pathname' is the pathname of the image, put in full pathname

        * 'shape' is a dictionary with keys 'r', 'c', and 'channels'

            * 'c': number of columns

            * 'r': number of rows

            * 'channels': number of channels

    * 'objects' is a list of dictionaries, where each dictionary has keys 'bounding_box', 'category'

        * 'bounding_box' is a dictionary with keys 'minimum' and 'maximum'

            * 'minimum': dictionary with keys 'r' and 'c'

                * 'r': smallest bounding box row

                * 'c': smallest bounding box column

            * 'maximum': dictionary with keys 'r' and 'c'

                * 'r': largest bounding box row

                * 'c': largest bounding box column

        * 'category' is a string denoting the class name

Suppose this data is save in a file called training.json. To load data,

.. code:: python

    import json

    with open('training.json') as f:

        d = json.load(f)

Slack

-----

We’ve been meeting in the #keras-rcnn channel on the keras.io Slack

server. 

You can join the server by inviting yourself from the following website:

https://keras-slack-autojoin.herokuapp.com/