PTQ-SL: Exploring the Sub-layerwise Post-training Quantization

TL;DR

This paper introduces PTQ-SL, a post-training quantization method using sub-layerwise granularity, and shows that channel reordering can enhance quantization performance, outperforming traditional channelwise methods.

Contribution

The paper explores a new sub-layerwise quantization granularity and proposes channel reordering to improve neural network quantization accuracy.

Findings

Sub-layerwise quantization accuracy correlates with granularity.

Channel reordering improves sub-layerwise quantization performance.

Sub-layerwise quantization can outperform channelwise methods.

Abstract

Network quantization is a powerful technique to compress convolutional neural networks. The quantization granularity determines how to share the scaling factors in weights, which affects the performance of network quantization. Most existing approaches share the scaling factors layerwisely or channelwisely for quantization of convolutional layers. Channelwise quantization and layerwise quantization have been widely used in various applications. However, other quantization granularities are rarely explored. In this paper, we will explore the sub-layerwise granularity that shares the scaling factor across multiple input and output channels. We propose an efficient post-training quantization method in sub-layerwise granularity (PTQ-SL). Then we systematically experiment on various granularities and observe that the prediction accuracy of the quantized neural network has a strong correlation with the granularity. Moreover, we find that adjusting the position of the channels can improve the performance of sub-layerwise quantization. Therefore, we propose a method to reorder the channels for sub-layerwise quantization. The experiments demonstrate that the sub-layerwise quantization with appropriate channel reordering can outperform the channelwise quantization.