Adaptive quantization and mixed precision in a network
US11507823B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Apr 10, 2019 |
| Grant date | Nov 22, 2022 |
| Priority date | — |
| Expiry date | Sep 22, 2041 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06F2207/4824
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A method of adaptive quantization for a convolutional neural network, includes at least one of receiving an acceptable model accuracy, determining a float value multiply accumulate for the layer based on a float value weight and a float value input, quantizing the float value weight at multiple weight quantization precisions, quantizing the float value input at multiple input quantization precisions, determining a multiply accumulate at multiple multiply accumulate quantization precisions based on the weight quantization precisions and the input quantization precisions, determining multiple quantization errors based on differences between the float value multiply accumulate and the multiple multiply accumulate quantization precisions and selecting one of the multiple weight quantization precisions, one of the multiple input quantization precisions and one of the multiple multiply accumulate quantization precisions based on the predetermined acceptable model accuracy and the multiple quantization errors.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.