一种改进的神经网络量化校准方法
本发明提供一种改进的神经网络量化校准方法,包括:S1.构建校准数据集;S2.保存浮点神经网络特征图;S3.量化神经网络输入;S4.校准量化参数;S5,量化权重;S6.量化特征图;S7,量化效果评估。这项改进为现有的校准方法提供了有效的补充,提高了校准过程的鲁棒性,减少由于极端情况导致的量化异常,从而提高了神经网络的可靠性,在实际应用中具有重要意义。
APPLICANTS
Browse source applicant names and unchanged name fields from imported patent records.
These are name-based results, not verified legal entities. Identical names may refer to different people or organizations; aliases and historical names are not merged.
This page matches the complete original name field. It may contain multiple applicants or another recorded party role. Name boundaries and legal identities have not been verified; punctuation is preserved, not split.
3 indexed patent records
Patent counts refer to distinct records held by this site, not an applicant’s complete portfolio. A joint name field is not a single company.
Verified corpus date coverage and last import time are not currently available. Publication dates on patent records are not import dates. Cached directory results may lag behind new imports.
Search the local original applicant field containing this full text. Results may include joint lists or longer names; this is not an exact identity search.
Search patents with this applicant condition