Convolutional neural network feature map data compression method and device

A convolutional neural network and data compression technology, applied in the field of convolutional neural network, can solve problems such as high hardware overhead, high sparsity, and inappropriateness, and achieve the effect of increasing sparsity, enhancing potential, and increasing compression rate

CN112906874APending Publication Date: 2021-06-04NANJING UNIV
0 Cites 1 Cited by

Patent Information

Authority / Receiving Office
CN · China
Current Assignee / Owner
Publication Date
2021-06-04

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention discloses a convolutional neural network feature map data compression method and device. The method comprises a feature map channel reconstruction stage and a zero-value bit map coding compression stage. In the feature map channel reconstruction stage, feature map channel dimensions are reconstructed by using one-dimensional discrete cosine transform, high-frequency information filtering is realized by using a frequency domain filter, a sparse feature map of which the sparseness is higher than that of an original feature map is obtained, and then the sparse feature map is compressed in the zero-value bit map coding compression stage, and final compressed data of the original feature map is obtained. According to the method, channel redundancy of the convolutional neural network is utilized, channel groups with certain frequency domain features are reconstructed together, the sparseness of the data to be transmitted is improved, the compressed potential is further improved, then zero-value bit map coding compression is used for compressing the sparse feature map, and the compression rate is improved.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The present application relates to the technical field of convolutional neural networks, in particular to a data compression method and device for feature maps of convolutional neural networks. Background technique

[0002] In the field of machine vision, the network architecture with convolutional neural network as feature extractor has excellent accuracy and high computational efficiency. The convolutional neural network is composed of several or even hundreds of convolution operation layers stacked and connected. Based on the two-dimensional plane convolution calculation, the feature extraction of the image is performed to obtain the feature map data.

[0003] In practical applications, the convolutional neural network is usually deployed to a hardware accelerator or other low-power devices. After the feature map data is generated by the activation function in the convolutional neural network, it is transmitted to the off-chip memory of the hardware...

Examples

Embodiment Construction

[0054] In order to reduce hardware complexity to the greatest extent while increasing the compression rate, the present application discloses a convolutional neural network feature map data compression method and device through the following embodiments.

[0055] The first embodiment of the present application discloses a convolutional neural network feature map data compression method, including a feature map channel reconstruction stage and a zero-value bitmap encoding and compression stage.

[0056] The feature map channel reconstruction stage includes the following steps:

[0057] Change the channel dimension of the original feature map from three-dimensional segmentation to two-dimensional to obtain a new feature map.

[0058] The original feature map is X∈R C×H×W, where X represents the tensor in the original feature map, R represents the real number field, and the channel dimensions of the original feature map are three-dimensional, which are C, H, and W respectively. ...