Constrained Optimization Based Low-Rank Approximation of Deep Neural Networks

1 code implementation • ECCV 2018 • Chong Li, C. J. Richard Shi

We present COBLA---Constrained Optimization Based Low-rank Approximation---a systematic method of finding an optimal low-rank approximation of a trained convolutional neural network, subject to constraints in the number of multiply-accumulate (MAC) operations and the memory footprint.