Pruning method of convolutional neural network

The embodiment of the invention relates to the technical field of network compression, in particular to a convolutional neural network pruning method, and the method comprises the steps: inputting sample data into a target model, and obtaining a feature map outputted by each filter of each layer of the target model; traversing the filter, flattening the feature map output by the current filter, and calculating the internal feature activeness of the current filter according to the flattened feature map corresponding to the current filter; calculating the feature difference degree between every two flattened feature maps, and determining the substitutability score of the current filter according to the feature difference degree between the flattened feature map corresponding to the current filter and the flattened feature maps corresponding to other filters; and determining an importance score based on the internal feature activeness and the substitutability score, and pruning the current layer according to a p