论文标题
SIPA：有效网络的简单框架
SIPA: A Simple Framework for Efficient Networks
论文作者
论文摘要
随着在各个领域进行深度学习的成功以及众多物联网（IoT）设备的出现，因此减轻适合低功率设备的模型至关重要。为了与这一趋势保持一致，Micronet挑战是从存储和计算的视图中建立有效模型的挑战，在Neurips 2019上托管了。为了通过这项挑战开发有效的模型，我们提出了一个框架，即SIPA，由四个阶段组成：搜索，改进，修剪，修剪和加速。通过提出的框架，我们的团队OSI AI压缩了334X参数存储，而357X的数学操作与WideSnet-28-10相比，在Micronet Challenge 2019中获得了CIFAR-100赛道的第四名，并获得了最高10％的高效计算。我们的源代码可从https://github.com/lee-gihun/micronet_osi-ai获得。
With the success of deep learning in various fields and the advent of numerous Internet of Things (IoT) devices, it is essential to lighten models suitable for low-power devices. In keeping with this trend, MicroNet Challenge, which is the challenge to build efficient models from the view of both storage and computation, was hosted at NeurIPS 2019. To develop efficient models through this challenge, we propose a framework, coined as SIPA, consisting of four stages: Searching, Improving, Pruning, and Accelerating. With the proposed framework, our team, OSI AI, compressed 334x the parameter storage and 357x the math operation compared to WideResNet-28-10 and took 4th place in the CIFAR-100 track at MicroNet Challenge 2019 with the top 10% highly efficient computation. Our source code is available from https://github.com/Lee-Gihun/MicroNet_OSI-AI.
