Method and device for compressing neural network model, equipment and medium
A technology of neural network model and compression ratio, which is applied in the field of artificial intelligence and deep learning, can solve the problems of difficult deployment, large amount of calculation and storage space occupied, and limited application of convolutional neural network, so as to reduce the amount of calculation, The effect of reducing the number of
Pending Publication Date: 2021-07-02
SHANGHAI BILIBILI TECH CO LTD
View PDF4 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Correspondingly, the amount of calculation and the storage space occupied by the convolutional neural network are increasing, which leads to the limited application of the convolutional neural network, and it is difficult to deploy and run on devices with limited computing power and storage space (such as personal computers, Mobile phones, tablets, smart wearable devices, etc.)
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0019] Exemplary embodiments of the present disclosure are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present disclosure to facilitate understanding, and they should be regarded as exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
[0020] In the present disclosure, unless otherwise stated, using the terms "first", "second", etc. to describe various elements is not intended to limit the positional relationship, temporal relationship or importance relationship of these elements, and such terms are only used for Distinguishes one element from another. In some examples, the first element and the second ...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention provides a method and device for compressing a neural network model, equipment and a medium, and relates to the technical field of artificial intelligence, in particular to the technical field of deep learning. According to the scheme, the method comprises the steps that a first neural network model is obtained, the first neural network model comprises a plurality of convolution channels and batch standardization channels corresponding to the convolution channels, and the batch standardization channels have importance parameters used for representing the importance degree of the corresponding convolution channels; the method also includes determining at least one secondary channel from a first subset of the plurality of convolutional channels based on the respective importance parameter; determining redundant parameters respectively corresponding to the convolution channels in the second subset of the plurality of convolution channels, wherein the redundant parameters are used for representing the redundancy degree of the corresponding convolution channels; determining at least one redundant channel from the second subset based on a corresponding redundant parameter; and constructing a compressed second neural network model based on the remaining convolution channels.
Description
technical field [0001] The present disclosure relates to the technical field of artificial intelligence, in particular to the technical field of deep learning, and in particular to a method, device, electronic equipment, computer-readable storage medium and computer program product for compressing a neural network model. Background technique [0002] Convolutional neural network is one of the representative algorithms of deep learning, and is widely used in tasks in the fields of speech recognition, image / video processing, and natural language processing. With the complexity of processing tasks, the scale of convolutional neural networks continues to expand. Correspondingly, the amount of calculation and the storage space occupied by the convolutional neural network are increasing, which leads to the limited application of the convolutional neural network, and it is difficult to deploy and run on devices with limited computing power and storage space (such as personal comput...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & AuthorityApplications(China)
IPC IPC(8): G06N3/04G06N3/08G06N5/04
CPCG06N3/084G06N5/04G06N3/045
Inventor鲁超
OwnerSHANGHAI BILIBILI TECH CO LTD