MorphNet: Fast & Simple Resource-Constrained Structure Learning of Deep Networks

Code

• github.com/tensorflow/models
  tf★ 77,694
• github.com/google-research/morph-net
  tf★ 1,032
• github.com/NatGr/Master_Thesis
  tf★ 0

Abstract

We present MorphNet, an approach to automate the design of neural network structures. MorphNet iteratively shrinks and expands a network, shrinking via a resource-weighted sparsifying regularizer on activations and expanding via a uniform multiplicative factor on all layers. In contrast to previous approaches, our method is scalable to large networks, adaptable to specific resource constraints (e.g. the number of floating-point operations per inference), and capable of increasing the network's performance. When applied to standard network architectures on a wide variety of datasets, our approach discovers novel structures in each domain, obtaining higher performance while respecting the resource constraint.

Tasks

Reproductions