Lossless model compression by batch normalization layer pruning in deep neural networks
US11488019B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Jan 24, 2019 |
| Grant date | Nov 1, 2022 |
| Priority date | — |
| Expiry date | Dec 26, 2040 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N3/0495
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A method of pruning a batch normalization layer from a pre-trained deep neural network model is proposed. The pre-trained deep neural network model is inputted as a candidate model. The candidate model is pruned by removing the at least one batch normalization layer from the candidate model to form a pruned candidate model only when the at least one batch normalization layer is connected to and adjacent to a corresponding linear operation layer. The corresponding linear operation layer may be at least one of a convolution layer, a dense layer, a depthwise convolution layer, and a group convolution layer. Weights of the corresponding linear operation layer are adjusted to compensate for the removal of the at least one batch normalization. The pruned candidate model is then output and utilized for inference.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.