Unlock instant, AI-driven research and patent intelligence for your innovation.

Off-line model verification method and related device

An offline model and verification method technology, applied in the field of data processing, can solve the problem of low efficiency of offline models and achieve the effect of improving efficiency

Active Publication Date: 2020-12-18
ANHUI CAMBRICON INFORMATION TECH CO LTD
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

When performing forward propagation verification on the offline model in the existing scheme, it is necessary to perform complex processing such as input data pre-processing and input data post-processing, so that the forward propagation of the offline model can be verified, resulting in the Less efficient when doing forward pass validation

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Off-line model verification method and related device
  • Off-line model verification method and related device
  • Off-line model verification method and related device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0057] In the embodiment of the present application, it aims to solve the problem that in the prior art, when performing the verification of the forward propagation of the offline model, the method adopted needs to go through complex parameter construction and parameter processing. It is proposed that by constructing the test data, the test data is Randomly generated data and the size of the test data is the same as the size of the input data of the offline model, the test data is input into the offline model for forward propagation calculation, so as to verify the forward propagation of the offline model, in order to improve the offline model Efficiency of the model during forward-propagation validation.

[0058] The following will clearly and completely describe the technical solutions in the embodiments of the application with reference to the drawings in the embodiments of the application. Apparently, the described embodiments are only some of the embodiments of the applica...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The embodiment of the invention provides an offline model verification method and a related device. The method comprises the following steps of: constructing test data, and inputting the test data into an offline model to carry out forward propagation calculation, so as to verify the forward propagation of the offline model, thereby improving the efficiency of carrying out forward propagation verification on the offline model.

Description

technical field [0001] The present application relates to the technical field of data processing, in particular to a verification method and a related device of an offline model. Background technique [0002] With the development of science and technology, artificial intelligence technology has been paid more and more attention by people. In artificial intelligence technology, neural networks are used to process data, and deep learning is usually used in the training of neural networks. The forward propagation process of deep learning is generally divided into two types: online forward propagation and offline forward propagation. The framework is an efficient operation mode. The offline model is generated by the deep learning framework program according to the given network structure and weight data. The offline model contains information such as MLU offline instructions, weight data, model data, and subnetworks. In actual use, the offline model will be deployed in actua...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06N3/08
CPCG06N3/08
Inventor 不公告发明人
Owner ANHUI CAMBRICON INFORMATION TECH CO LTD