Keras API
Keras has a modular, minimalist, and easy extendable architecture. Francois Chollet, the author of Keras, says:
The library was developed with a focus on enabling fast experimentation. Being able to go from idea to result with the least possible delay is key to doing good research.
Keras defines high-level neural networks running on top of either TensorFlow (for more information, refer to https://github.com/tensorflow/tensorflow) or Theano (for more information, refer to https://github.com/Theano/Theano). In details:
- Modularity: A model is either a sequence or a graph of standalone modules that can be combined together like LEGO blocks for building neural networks. Namely, the library predefines a very large number of modules implementing different types of neural layers, cost functions, optimizers, initialization schemes, activation functions, and regularization schemes.
- Minimalism: The library is implemented in Python and each module is kept short and self-describing.
- Easy extensibility...