论文标题
PFGDF：通过高斯分布特征的修剪过滤器，用于深神经网络加速
PFGDF: Pruning Filter via Gaussian Distribution Feature for Deep Neural Networks Acceleration
论文作者
论文摘要
深度学习在许多领域都取得了令人印象深刻的成果，但是Edge Intellighent设备的部署仍然非常慢。为了解决这个问题，我们提出了一种基于深神经网络的数据分布特征的新型压缩和加速方法，即通过高斯分布特征（PFGDF）修剪过滤器。与以前的高级修剪方法相比，PFGDF通过分布无关的过滤器压缩模型，而不管卷积过滤器的贡献和灵敏度信息如何。 PFGDF与重量稀疏修剪明显不同，因为它不需要特殊的加速库来处理稀疏的权重矩阵，并且不再引入额外的参数。 PFGDF的修剪过程是自动化的。此外，PFGDF压缩的模型可以恢复与未压缩模型相同的性能。我们通过广泛的实验评估PFGDF，在CIFAR-10上，PFGDF在VGG-16上压缩了VGG-16上的卷积过滤器66.62％，降低了90％以上的参数，而推理时间则在HUAWEI MATE 10上加速了83.73％。
Deep learning has achieved impressive results in many areas, but the deployment of edge intelligent devices is still very slow. To solve this problem, we propose a novel compression and acceleration method based on data distribution characteristics for deep neural networks, namely Pruning Filter via Gaussian Distribution Feature (PFGDF). Compared with previous advanced pruning methods, PFGDF compresses the model by filters with insignificance in distribution, regardless of the contribution and sensitivity information of the convolution filter. PFGDF is significantly different from weight sparsification pruning because it does not require the special accelerated library to process the sparse weight matrix and introduces no more extra parameters. The pruning process of PFGDF is automated. Furthermore, the model compressed by PFGDF can restore the same performance as the uncompressed model. We evaluate PFGDF through extensive experiments, on CIFAR-10, PFGDF compresses the convolution filter on VGG-16 by 66.62% with more than 90% parameter reduced, while the inference time is accelerated by 83.73% on Huawei MATE 10.
