Neural Network Distiller: A Python Package For DNN Compression Research
It offers a practical toolkit for researchers and engineers working on DNN compression, but it is incremental as it packages existing methods rather than proposing new ones.
The paper introduces Neural Network Distiller, an open-source Python package designed for DNN compression research, providing implementations of compression algorithms, tools, tutorials, and sample applications to support engineers and researchers.
This paper presents the philosophy, design and feature-set of Neural Network Distiller, an open-source Python package for DNN compression research. Distiller is a library of DNN compression algorithms implementations, with tools, tutorials and sample applications for various learning tasks. Its target users are both engineers and researchers, and the rich content is complemented by a design-for-extensibility to facilitate new research. Distiller is open-source and is available on Github at https://github.com/NervanaSystems/distiller.