基于相量的FFT加速CNN方法
Phasor-Driven Acceleration for FFT-based CNNs
AI总结:
本文提出使用相量形式替代传统直角坐标表示,通过极坐标复数运算优化FFT-based CNN的频域计算,在CIFAR-10/100上实现1.3-1.4倍训练推理加速,且可无缝集成到现有卷积模型中。
摘要:
深度学习(DL)领域的最新研究探索了利用快速傅里叶变换(FFT)加速卷积神经网络(CNNs)中的计算,通过将空间卷积替换为频域上的逐元素乘法来实现。这些方法主要依赖FFT来减少运算次数,而采用实值FFT可进一步降低运算量。本文提出使用相量形式(phasor form),即复数的极坐标表示,作为传统方法的更高效替代方案。在CIFAR-10数据集上的实验结果表明,与现代CNN架构中传统使用的直角坐标形式相比,本方法在训练阶段实现了最高1.376倍(平均1.316倍)的速度提升,在推理阶段达到最高1.390倍(平均1.321倍)。类似地,在CIFAR-100数据集上的评估显示,该方法在训练阶段实现最高1.375倍(平均1.299倍)的加速,推理阶段达到最高1.387倍(平均1.300倍)。最重要的是,由于本方法具有模块化特性,可直接应用于任何现有的基于卷积的DL模型而无需修改设计。
英文摘要:
Recent research in deep learning (DL) has investigated the use of the Fast Fourier Transform (FFT) to accelerate the computations involved in Convolutional Neural Networks (CNNs) by replacing spatial convolution with element-wise multiplications on the spectral domain. These approaches mainly rely on the FFT to reduce the number of operations, which can be further decreased by adopting the Real-Valued FFT. In this paper, we propose using the phasor form, a polar representation of complex numbers, as a more efficient alternative to the traditional approach. The experimental results, evaluated on the CIFAR-10, demonstrate that our method achieves superior speed improvements of up to a factor of 1.376 (average of 1.316) during training and up to 1.390 (average of 1.321) during inference when compared to the traditional rectangular form employed in modern CNN architectures. Similarly, when evaluated on the CIFAR-100, our method achieves superior speed improvements of up to a factor of 1.375 (average of 1.299) during training and up to 1.387 (average of 1.300) during inference. Most importantly, given the modular aspect of our approach, the proposed method can be applied to any existing convolution-based DL model without design changes.
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。