Quantisation and Pruning for Neural Network Compression and Regularisation

14 Jan 2020Kimessha PaupamahSteven JamesRichard Klein

Deep neural networks are typically too computationally expensive to run in real-time on consumer-grade hardware and low-powered devices. In this paper, we investigate reducing the computational and memory requirements of neural networks through network pruning and quantisation... (read more)

PDF Abstract

Evaluation Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK COMPARE
Neural Network Compression CIFAR-10 MobileNet – Quantised Size (MB) 2.9 # 2
Neural Network Compression CIFAR-10 ShuffleNet – Quantised Size (MB) 1.9 # 1
Neural Network Compression CIFAR-10 AlexNet – Quantised Size (MB) 54.6 # 3
Network Pruning CIFAR-10 MobileNet – Quantised Inference Time (ms) 4.74 # 1
Network Pruning CIFAR-10 ShuffleNet – Quantised Inference Time (ms) 23.15 # 3
Network Pruning CIFAR-10 AlexNet – Quantised Inference Time (ms) 5.23 # 2