Finding out the computational redundant part of a trained Deep Neural Network
(DNN) is the key question that pruning algorithms target on. Many algorithms
try to predict model performance of the pruned sub-nets by introducing various
evaluation methods. But they are either inaccurate or very complicated for
general application. In this work, we present a pruning method called EagleEye,
in which a simple yet efficient evaluation component based on adaptive batch
normalization is applied to unveil a strong correlation between different
pruned DNN structures and their final settled accuracy. This strong correlation
allows us to fast spot the pruned candidates with highest potential accuracy
without actually fine-tuning them. This module is also general to plug-in and
improve some existing pruning algorithms. EagleEye achieves better pruning
performance than all of the studied pruning algorithms in our experiments.
Concretely, to prune MobileNet V1 and ResNet-50, EagleEye outperforms all
compared methods by up to 3.8%. Even in the more challenging experiments of
pruning the compact model of MobileNet V1, EagleEye achieves the highest
accuracy of 70.9% with an overall 50% operations (FLOPs) pruned. All accuracy
results are Top-1 ImageNet classification accuracy. Source code and models are
accessible to open-source community
this https URL .

本文提出了一种名为 EagleEye 的剪枝算法，利用简单且高效的自适应批量归一化评估方法来加速识别潜在精度最高的剪枝候选项，从而更好地裁剪神经网络。在 MobileNet V1 和 ResNet-50 等模型中进行实验表明，EagleEye 优于所有已有的算法，FLOPs 剪枝达到 50% 时，对于 MobileNet V1 模型，EagleEye 实现了 70.9% 的 Top-1 ImageNet 模型分类精度。