arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1906.04798cs.LGstat.ML
收藏

基于表格的神经单元:用于无多重干扰推理的完全量化网络

Table-Based Neural Units: Fully Quantizing Networks for Multiply-Free Inference

Google Research(谷歌研究院)

Michele Covell, David Marwood, Shumeet Baluja, Nick Johnston

摘要:

在这项工作中,我们建议将标准分类网络的所有部分合并,并用一个简单的基于表的查找来代替激活权重乘法步骤。这种方法导致网络无需浮点运算和乘法,适合直接FPGA和ASIC实现。它还为我们提供了每层和网络范围紧凑性的两个简单度量,以及对激活输出和权重值的分布特性的洞察。我们在不同的量化方案,固定的和自适应的,并在一组自适应方法,参数和无模型的控制研究。我们通过对训练过程进行最小的局部化更改来实现我们的量化方法,使我们能够受益于训练连续值网络架构的进步。我们成功地将我们的方法应用于AlexNet,ResNet和MobileNet。我们显示的结果是在1.6%的报告,非量化的性能在MobileNet上使用我们的表中只有40个条目。当我们允许有320个条目的表时,这个性能差距缩小到零。我们的研究结果给出了最好的精度之间的乘法自由网络。

英文摘要:

In this work, we propose to quantize all parts of standard classification networks and replace the activation-weight--multiply step with a simple table-based lookup. This approach results in networks that are free of floating-point operations and free of multiplications, suitable for direct FPGA and ASIC implementations. It also provides us with two simple measures of per-layer and network-wide compactness as well as insight into the distribution characteristics of activationoutput and weight values. We run controlled studies across different quantization schemes, both fixed and adaptive and, within the set of adaptive approaches, both parametric and model-free. We implement our approach to quantization with minimal, localized changes to the training process, allowing us to benefit from advances in training continuous-valued network architectures. We apply our approach successfully to AlexNet, ResNet, and MobileNet. We show results that are within 1.6% of the reported, non-quantized performance on MobileNet using only 40 entries in our table. This performance gap narrows to zero when we allow tables with 320 entries. Our results give the best accuracies among multiply-free networks.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑