提出一种新型1D-CNN推理方案，降低边缘设备延迟并减少内存占用。
A 1-D CNN inference engine for constrained platforms
- 在采样间隔间交错执行卷积，避免阻塞数据采集
- 相比TFLite，推理延迟降10%，内存使用几乎减半
- 适用于资源受限的消费级设备，如Arduino
1D-CNN在多个领域中用于时间序列分类，精度较高。现有实现通常将输入数据先存入缓冲区再进行推理，在单线程、资源受限的边缘设备上可能干扰关键采样任务。本文提出一种推理方案，将卷积操作交错安排在采样间隔之间，有效降低推理延迟。该方案适合采用环形缓冲区存储数据，显著减少内存占用。通过与TFLite对比验证，本方法在推理延迟上减少10%，内存使用量几乎减半。实验在基于AVR和ARM的Arduino板上完成，证明其在常见消费级设备上的可行性。
原文摘要 · Abstract (English)
1D-CNNs are used for time series classification in various domains with a high degree of accuracy. Most implementations collect the incoming data samples in a buffer before performing inference on it. On edge devices, which are typically constrained and single-threaded, such an implementation may interfere with time-critical tasks. One such task is that of sample acquisition. In this work, we propose an inference scheme that interleaves the convolution operations between sample intervals, which allows us to reduce the inference latency. Furthermore, our scheme is well-suited for storing data in ring buffers, yielding a small memory footprint. We demonstrate these improvements by comparing our approach to TFLite's inference method, giving a 10% reduction in the inference delay while almost halving the memory usage. Our approach is feasible on common consumer devices, which we show using an AVR-based Arduino board and an ARM-based Arduino board.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。