Method for deep convolutional neural network model compression

Abstract

The invention discloses a method for deep convolutional neural network model compression. The method comprises the steps that a trained deep convolutional neural network model is retrained to remove redundant network connections; weights of remaining connections of various network layers of a convolutional neural network are coded; the weights of the remaining connections of the various network layers of the convolutional neural network are subjected to k-means clustering; clustering results are subjected to fine tuning; and results after fine tuning are saved, and a saved file is subjected toHuffman coding. According to the method, by setting a dynamic threshold, the connections in the network can be gently removed to enable the network to be recovered from the unfavorable condition thatthe connections are removed, and therefore the effect that the compression multiples is high under the condition of the same accuracy rate loss can be achieved; and in the coding process of the remaining connections, the bit number needed for representing an index value can be decreased by means of the used improved CSR coding method, therefore, the size of the compressed file can be decreased, and the compression ratio is increased.

Description

technical field [0001] The invention relates to the fields of deep learning and artificial intelligence, in particular to a method for compressing a deep convolutional neural network model. Background technique [0002] In recent years, deep learning algorithms have achieved a series of amazing results in the field of artificial intelligence, and deep convolutional neural networks are currently one of the most widely used and successful deep learning algorithms in the field of computer vision, a branch of artificial intelligence. . Generally speaking, in order to solve more complex computer vision problems, it is necessary to introduce more neurons or increase the number of layers of the network in the convolutional neural network, but this will inevitably lead to more parameters in the network and a larger network model. For example, the model size of the AlexNet deep convolutional neural network used to solve the classification problem of the ImageNet dataset reaches 243....

AI Technical Summary

Problems solved by technology

Generally speaking, in order to solve more complex computer vision problems, it is necessary to introduce more neurons or increase the number of layers of the network in the convolutional neural network, but this will inevitably lead to more parameters in the network and a larger network model

For example, the model size of the AlexNet deep convolutional neural network used to solve the classification problem of the ImageNet dataset reaches 243.9M. Obviously, a model of this size cannot be deployed on mobile terminals or embedded devices with very limited storage space.

Images