Abstract: Aiming at the problem that the accuracy of the network model would drop sharply with the imbalance of the network structure when the traditional layer-wise  pruning method was in the later stage of the pruning process， we proposed a layer-wise pruning method based on network characteristics. Firstly, the pruning coefficient of each iteration was calculated according to the network depth, network width and inter-layer importance index. Secondly,  the dynamic pruning rate of each layer parameter was obtained by combining the basic pruning rate. Finally, pruned and fine tuned the pre-trained network, and repeated the above process to the end of iteration. The experimental results show that the layer-wise pruning method based on network characteristics performs 
well on VGG-16 model. When the compression rate is about double, the accuracy is still 3.6% higher than that of the layer-wise pruning method with single pruning rate, and the overall performance is better than that of the global pruning method. When the compression rate reaches more than 98.85%, the accuracy on the Resnet-20 model is 20% higher than that of the layer-wise method with single pruning rate, which is close to the global pruning method. It shows that  the performance of layer-wise pruning method can be improved by making full use of network characteristics.

Key words:  , network characteristics, layer-wise pruning, iterative pruning, model compression