使用参数的低位量化来减少深度神经网络的内存需求
Memory Requirement Reduction of Deep Neural Networks Using Low-bit Quantization of Parameters
摘要:
深度神经网络(DNN)在移动设备和嵌入式系统中的有效应用受到内存和计算能力要求的阻碍。本文提出了一种非均匀量化方法,该方法允许对不同层和同一层内的DNN参数进行动态量化。为了提高该方案的准确性,还提出了一种虚拟比特移位(VBS)方案。我们的方法降低了内存需求,保持了网络的性能。在一个语音增强应用中,我们的方法的性能得到了验证,其中一个完全连接的DNN被用来从输入的噪声语音频谱预测干净的语音频谱。DNN被优化,其内存占用和性能使用短时客观可懂度(STOI)指标进行评估。低位量化的应用允许DNN内存占用减少50%,而STOI性能仅下降2.7%。
英文摘要:
Effective employment of deep neural networks (DNNs) in mobile devices and embedded systems is hampered by requirements for memory and computational power. This paper presents a non-uniform quantization approach which allows for dynamic quantization of DNN parameters for different layers and within the same layer. A virtual bit shift (VBS) scheme is also proposed to improve the accuracy of the proposed scheme. Our method reduces the memory requirements, preserving the performance of the network. The performance of our method is validated in a speech enhancement application, where a fully connected DNN is used to predict the clean speech spectrum from the input noisy speech spectrum. A DNN is optimized and its memory footprint and performance are evaluated using the short-time objective intelligibility, STOI, metric. The application of the low-bit quantization allows a 50% reduction of the DNN memory footprint while the STOI performance drops only by 2.7%.
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。