提出可统一比较的剪枝框架，实现高效模型压缩与加速。
Bonsai: A Framework for Convolutional Neural Network Acceleration Using Criterion-Based Pruning
- 基于剪枝准则构建通用框架，支持多种剪枝策略
- 在VGG类模型上剪除79%滤波器，计算量降低68%且精度不降
- 提供标准化评估语言，适合模型压缩研究者使用
随着对更精确、更强的卷积神经网络（CNN）需求增加，其规模、运行时间、内存占用和功耗也不断上升。为应对这一问题，已有剪枝方法被提出，但各自采用不同的剪枝指标和方法，缺乏统一实现，难以比较。本文提出Combine框架，一种基于剪枝准则的解决方案，证明其在迭代剪枝中快速有效；揭示不同剪枝准则对不同模型影响各异；建立标准化的准则比较语言，并提出若干新剪枝准则。在受VGG启发的模型上验证，最多可剪除79%的滤波器，同时保持或提升精度，并将网络计算量减少高达68%。
原文摘要 · Abstract (English)
As the need for more accurate and powerful Convolutional Neural Networks (CNNs) increases, so too does the size, execution time, memory footprint, and power consumption. To overcome this, solutions such as pruning have been proposed with their own metrics and methodologies, or criteria, for how weights should be removed. These solutions do not share a common implementation and are difficult to implement and compare. In this work, we introduce Combine, a criterion- based pruning solution and demonstrate that it is fast and effective framework for iterative pruning, demonstrate that criterion have differing effects on different models, create a standard language for comparing criterion functions, and propose a few novel criterion functions. We show the capacity of these criterion functions and the framework on VGG inspired models, pruning up to 79\% of filters while retaining or improving accuracy, and reducing the computations needed by the network by up to 68\%.
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。