With the proliferation of deep convolutional neural network (CNN) algorithms for mobile processing, limited precision quantization has become an essential tool for CNN efficiency. Consequently, various works have sought to design fixed precision quantization algorithms and quantization-focused optimization techniques that minimize quantization induced performance degradation. However, there is little concrete understanding of how various CNN design decisions/best practices affect quantized inference behaviour. Weight initialization strategies are often associated with solving issues such as vanishing/exploding gradients but an often-overlooked aspect is their impact on the final trained distributions of each layer. We present an in-depth, fine-grained ablation study of the effect of different weights initializations on the final distributions of weights and activations of different CNN architectures. The fine-grained, layerwise analysis enables us to gain deep insights on how initial weights distributions will affect final accuracy and quantized behaviour. To our best knowledge, we are the first to perform such a low-level, in-depth quantitative analysis of weights initialization and its effect on quantized behaviour.
翻译:随着移动处理的深度进化神经网络算法(CNN)的激增,有限的精确量化已成为CNN效率的基本工具,因此,各种工作都试图设计固定精确量化算法和以量化为重点的优化技术,以尽量减少四分化导致性能退化;然而,对于各种CNN设计决定/最佳做法如何影响量化推论行为,却缺乏具体了解。轻度初始化战略往往与诸如消失/爆炸梯度等问题的解决相关联,但经常被人们忽视的一个方面是其对每一层最后经过训练的分布的影响。我们提出了对不同重量初始化对重量最终分布和不同CNN结构的激活的不同加权初始化效应的深入、精细微的调整研究。精细的、分层分析使我们能够深入了解初始重量分布将如何影响最终精确度和四分化行为。据我们所知,我们是第一个对重量初始初始化及其对四分化行为的影响进行这种低层次、深入的定量分析。