PFGDF: Pruning Filter via Gaussian Distribution Feature for Deep Neural Networks Acceleration
This addresses the problem of model efficiency for edge device deployment, presenting an incremental improvement over existing pruning methods.
The paper tackles the slow deployment of deep neural networks on edge devices by proposing PFGDF, a pruning method that compresses models based on Gaussian distribution features, achieving 66.62% filter compression and 83.73% inference acceleration on VGG-16 with CIFAR-10 while restoring original performance.
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.