Double-layer same-or binary neural network compression method based on lookup table calculation

Abstract

The invention discloses a double-layer same or binary neural network compression method based on lookup table calculation. The compression method is completed by a double-layer convolution structure,and the algorithm comprises the following steps: firstly, performing non-linear activation, batch normalization and binary activation on an input feature map, and grouping to perform first-layer convolution operation with different convolution kernel sizes to obtain a first-layer output result; and then, carrying out 1 * 1 second-layer convolution operation on the first-layer output result to obtain an output feature map. In terms of hardware implementation, a traditional double-layer sequential calculation mode is replaced by three-input XOR operation of double-layer parallel calculation forimproved double-layer convolution, all double-layer convolution operations are calculated in a lookup table mode, and the utilization rate of hardware resources is increased. The compression method provided by the invention is an algorithm hardware collaborative compression scheme integrating a full-precision high-efficiency neural network technique and a lookup table calculation mode, has a relatively good compression effect in structure, and also reduces the consumption of logic resources in hardware.

Description

technical field [0001] The invention relates to an FPGA optimization design technology of a binary neural network, belonging to the technical field of digital image processing. Background technique [0002] Based on the vigorous development of deep learning technology, convolutional neural network (CNN) has been widely used in the field of digital image processing. Starting from the most classic AlexNet, to the ResNet residual neural network proposed by Facebook Research Institute, the deep convolutional neural network has entered a period of rapid development, and the performance of the neural network is gradually increasing. In terms of practical applications, Google has achieved remarkable results in autonomous driving and face recognition using convolutional neural networks. At the same time, the convolutional neural network has encountered some challenges in the process of development. For example, the high computational load and high complexity of the convolutional ne...

AI Technical Summary

Problems solved by technology

[0007] However, the power consumption and logic resource consumption of this structure are relatively large

Images