Keras is a high-level neural networks API, originall written in Python, and capable of running on top of either TensorFlow or Theano. It was developed with a focus on enabling fast experimentation. This package provides an interface to Keras from within R. All of the returned objects from functions in this package are either native R objects or raw pointers to python objects, making it possible for users to access the entire keras API. The main benefits of the package are (1) correct, manual parsing of R inputs to python, (2) R-sided documentation, and (3) examples written using the API. It allows, amongst other things, users to load and run popular pre-trained models such as VGG-19 (He et al. 2015), ResNet50 (He et al. 2016), and Inception (Szegedy et al. 2015).
Most functions have associated examples showing a working example of how a layer or object may be used. These are mostly toy examples, made with small datasets with little regard to whether these are the correct models for a particular task. See the package vignettes for a more thorough explaination and several larger, more practical examples.
He, Kaiming, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2015. “Delving Deep into Rectifiers: Surpassing Human-Level Performance on Imagenet Classification.” In Proceedings of the Ieee International Conference on Computer Vision, 1026–34.
———. 2016. “Deep Residual Learning for Image Recognition.” In Proceedings of the Ieee Conference on Computer Vision and Pattern Recognition, 770–78.
Szegedy, Christian, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, and Andrew Rabinovich. 2015. “Going Deeper with Convolutions.” In Proceedings of the Ieee Conference on Computer Vision and Pattern Recognition, 1–9.