Skip to main content
U.S. Department of Energy
Office of Scientific and Technical Information

Composability-Centered Convolutional Neural Network Pruning

Technical Report ·
DOI:https://doi.org/10.2172/1427608· OSTI ID:1427608
 [1];  [1];  [2];  [2]
  1. North Carolina State Univ., Raleigh, NC (United States)
  2. Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
This work studies the composability of the building blocks of structural CNN models (e.g., GoogleLeNet and Residual Networks) in the context of network pruning. We empirically validate that a network composed of pre-trained building blocks (e.g. residual blocks and Inception modules) not only gives a better initial setting for training, but also allows the training process to converge at a significantly higher accuracy in much less time. Based on that insight, we propose a composability-centered design for CNN network pruning. Experiments show that this new scheme shortens the configuration process in CNN network pruning by up to 186.8X for ResNet-50 and up to 30.2X for Inception-V3, and meanwhile, the models it finds that meet the accuracy requirement are significantly more compact than those found by default schemes.
Research Organization:
Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)
Sponsoring Organization:
USDOE
DOE Contract Number:
AC05-00OR22725
OSTI ID:
1427608
Report Number(s):
ORNL/TM-2018/777
Country of Publication:
United States
Language:
English

Similar Records

Related Subjects