CNN model compression method based on activation-entropy weight pruning
A compression method and model technology, applied in neural learning methods, biological neural network models, neural architectures, etc., can solve problems such as poor results, achieve the effect of reducing volume and ensuring calculation accuracy
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0051] The present invention will be further explained below in conjunction with the drawings.
[0052] In the CNN model compression method based on activation-entropy weight pruning in the present invention, since the CNN model parameters are mainly concentrated in the fully connected layer, the method pruning is mainly used in the fully connected layer. In the pruning process, each layer is pruned separately, and the activation-entropy criterion is used to judge the importance of each weight. Each layer of pruning process carries out multiple iterations. Retrain the model after each round of pruning to compensate for the loss of accuracy. When all the specified layers are pruned, the compressed CNN model is obtained.
[0053] ① Judgment of weight importance based on activation-entropy:
[0054] Aiming at activation-based and importance-based pruning methods, a CNN model pruning method based on activation-entropy weight is proposed.
[0055] Activation is used as the input of a ne...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap