Skip to content
Keras extended utilities
Branch: master
Clone or download
Latest commit dd39437 Aug 1, 2019

Keras extended Utilities for MLSP feature learning

The project contains tools for easier development with Keras/Tensorflow. It was developed for AVA-MLSP feature learning. The code in and pertains more to MLSP feature learning, wheras the remaining tools are general purpose.


Some of the key components of each file:

  • H5Helper: Manage named data sets in HDF5 files, for us in Keras generators.
  • pretty: Pretty-print dictionary type objects.
  • ShortNameBuilder: Utility for building short (file) names that contain multiple parameters.

  • ImageAugmenter: Create custom image augmentation functions for training Keras models.
  • read_image, read_image_batch: utility functions for manipulating images.

  • ModelHelper: Wrapper class that simplifies default usage of Keras for regression models.

  • model_inception_multigap, model_inceptionresnet_multigap: Model definitions for extracting MLSP narrow features
  • model_inception_pooled, model_inceptionresnet_pooled: Model definitions for extracting MLSP wide features

  • DataGeneratorDisk, DataGeneratorHDF5: Keras generators for on-disk images, and HDF5 stored features/images

You can find more information in the Python Docstrings.

You can’t perform that action at this time.