Mixing precision quantification method of network model, equipment and computer storage medium

• Main Authors: LYU NIQI, KANG RUIPENG, YOU LIANG, LONG XIN, CHENG WENHUA, FANG MINQUAN
• Format: Patent
• Language: Chinese; English
• Published: 28.09.2021
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; PHYSICS

The embodiment of the invention provides a mixing precision quantification method of a network model, equipment and a computer storage medium. The method comprises the steps: acquiring a network model and a configured network model corresponding to the network model, wherein data of network layers in the network model are of a first data type, data of at least one network layer in the configured network model are of a second data type, and the data processing precision corresponding to the second data type is lower than the data processing precision corresponding to the first data type; generating calibration data corresponding to the network model; processing the calibration data by using a network model to obtain a first processing result; processing the calibration data by using the configured network model to obtain a second processing result; and determining the sensitivity corresponding to at least one network layer in the network model based on the first processing result and the second processing resu