Command Palette
Search for a command to run...
Quantisation and Pruning for Neural Network Compression and Regularisation
Kimessha Paupamah Steven James Richard Klein
Abstract
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. We examine their efficacy on large networks like AlexNet compared to recent compact architectures: ShuffleNet and MobileNet. Our results show that pruning and quantisation compresses these networks to less than half their original size and improves their efficiency, particularly on MobileNet with a 7x speedup. We also demonstrate that pruning, in addition to reducing the number of parameters in a network, can aid in the correction of overfitting.
Code Repositories
Benchmarks
| Benchmark | Methodology | Metrics |
|---|---|---|
| network-pruning-on-cifar-10 | MobileNet – Quantised | Inference Time (ms): 4.74 |
| network-pruning-on-cifar-10 | ShuffleNet – Quantised | Inference Time (ms): 23.15 |
| network-pruning-on-cifar-10 | AlexNet – Quantised | Inference Time (ms): 5.23 |
| neural-network-compression-on-cifar-10 | MobileNet – Quantised | Size (MB): 2.9 |
| neural-network-compression-on-cifar-10 | AlexNet – Quantised | Size (MB): 54.6 |
| neural-network-compression-on-cifar-10 | ShuffleNet – Quantised | Size (MB): 1.9 |
Build AI with AI
From idea to launch — accelerate your AI development with free AI co-coding, out-of-the-box environment and best price of GPUs.