A software defined satellite adaptive pruning model compression method
A technology of software definition and compression method, which is applied in the direction of neural learning method, biological neural network model, neural architecture, etc., and can solve problems such as unsatisfactory requirements
Pending Publication Date: 2021-11-16
INST OF SOFTWARE - CHINESE ACAD OF SCI
View PDF9 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
In the traditional pruning method, a fixed pruning ratio is manually set for each layer in the network model, but as the number of network model layers increases and the network model becomes more and more complex, setting a fixed pruning ratio can no longer meet the requirements
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
[0047] In order to make the purposes, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only It is a part of the embodiments of this application, but not all of them. The components of the embodiments of the application generally described and illustrated in the figures herein may be arranged and designed in a variety of different configurations. Accordingly, the following detailed description of the embodiments of the application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely represents selected embodiments of the application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art wi...
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 embodiment of the invention provides a software defined satellite adaptive pruning model compression method. The method comprises the following steps: acquiring an ith to-be-pruned deep network model; obtaining the initial state of each layer in the ith to-be-pruned deep network model, wherein the initial state represents the attribute feature of each layer corresponding to the ith cycle, the initial state corresponding to the input layer is at least related to a preset initial pruning ratio, and the initial state in each remaining layer is at least related to the determined pruning ratio of the previous layer; inputting the initial state into a reinforcement learning pruning model for calculation to obtain an ith pruning ratio; repeating the process until a cycle termination condition is met, and obtaining a target pruning ratio of each layer; and compressing the to-be-pruned deep network model based on the target pruning ratio to obtain the target deep network model, so that the model can be compressed by automatically setting the pruning ratio, thereby accelerating the calculation speed of the model.
Description
technical field [0001] The embodiments of the present application relate to the field of deep network model compression, and in particular to a software-defined satellite self-adaptive pruning model compression method. Background technique [0002] In related technologies, in the process of model compression, the model is usually pruned by using a pruning ratio, so as to achieve the purpose of simplifying the model. In the traditional pruning method, a fixed pruning ratio is manually set for each layer in the network model, but as the number of network model layers increases and the network model becomes more and more complex, setting a fixed pruning ratio Than can no longer meet the requirements. [0003] Therefore, how to further improve the pruning ratio to compress the neural network model has become an urgent problem to be solved. Contents of the invention [0004] The embodiment of the present application provides a software-defined satellite adaptive pruning model...
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 & Authority Applications(China)
IPC IPC(8): G06N3/08G06N3/04
CPCG06N3/082G06N3/048G06N3/045
Inventor 吴凤鸽王文明赵军锁
Owner INST OF SOFTWARE - CHINESE ACAD OF SCI