Modellquantisierungsverfahren und -Vorrichtung sowie Vorrichtung und Speichermedium

Details

Veröffentlichungs-Nr.

EP4730205

Anmeldetag

12. Juli 2024

Veröffentlichung

23. Januar 2025

Rechtsraum

EP

IPC

G06N3/082, G06N3/0495

Abstract

A model quantization method and apparatus, and a device and a storage medium, which belong to the technical field of model quantization. The method comprises: acquiring a performance deviation corresponding to each model layer in a model to be quantized; constructing a hierarchical quantization sequence according to the performance deviations corresponding to the respective model layers; and performing hierarchical quantization processing on the model layers in said model on the basis of the hierarchical quantization sequence. A hierarchical quantization sequence is constructed according to performance deviations corresponding to respective model layers in a model to be quantized, hierarchical quantization processing is respectively performed on the model layers in said model according to the sequence order of the hierarchical quantization sequence, and after quantization during the processing parameter adjustment and correction are used to reduce a performance loss of the model to the greatest possible extent, which performance loss is generated by low-bit quantization.

Anmelder

Firma

Hangzhou Hikvision Digital Technology Co., Ltd.

Land

🇨🇳 China