Deep learning reasoning engine testing method based on differential evaluation

A technology of deep learning and reasoning engine, which is applied in the field of model processing of deep learning reasoning engine, which can solve the problems that deep learning compiler testing Oracle is difficult to solve, and the validity of a single output result is difficult to evaluate.

Pending Publication Date: 2020-10-30
深圳慕智科技有限公司
View PDF5 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The problem to be solved by the present invention is: the test Oracle of the deep learni...

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
  • Deep learning reasoning engine testing method based on differential evaluation
  • Deep learning reasoning engine testing method based on differential evaluation
  • Deep learning reasoning engine testing method based on differential evaluation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] Several key technologies involved in the present invention are to use some deep learning frameworks supported by inference engines to construct models, and use multiple inference engines to perform differential testing and test verification. The specific implementation uses deep learning to provide models to be tested Framework Caffe, Pytorch, Tensorflow, etc.

[0023] 1. Model information identification

[0024] In the present invention, we perform structural and property analysis on the model types that are input to the test. General neural network model information mainly includes framework dependencies, model operator lists and weights, etc. This information will be used in the model import phase to confirm whether the specific inference engine effectively supports the inference deployment for the model.

[0025] 2. Inference engine supports list generation

[0026] In the present invention, we obtain and analyze the inference engine involved in the test task, ma...

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 invention discloses a deep learning reasoning engine test method based on differential evaluation. A model import check module, an intermediate representation acquisition module and a result evaluation module are included. In the model import checking module, whether the engine supports all operators and related parameters involved in the model is analyzed, and whether the structure of the model is kept consistent after the model is imported into the engine is judged in combination with an exception capture mechanism in the engine and model structure comparison before and after import. Inthe middle representation acquisition module, IR data acquisition paths provided by different compilers are arranged, engine information and corresponding acquisition instructions are packaged throughmanual processing, and a unified calling interface is generated. In the result evaluation module, a compiler list suitable for the differential test task is obtained and includes a compiler name anda corresponding model source, and an intermediate representation obtaining interface is called to obtain IR data.

Description

technical field [0001] The invention belongs to the fields of software engineering and machine learning, in particular for model processing of a deep learning reasoning engine. For the intermediate process and output results processed by the deep learning model, evaluate the support of the inference engine for the specific deep learning framework. Background technique [0002] With the rapid development of artificial intelligence, neural network models based on deep learning (DL) technology have emerged and are widely used in cutting-edge fields such as autonomous driving and medical diagnosis. In order to provide convenient model training and deployment services, deep learning frameworks such as TensorFlow, PyTorch, and Caffe have emerged as needed. However, due to a series of problems such as platform support differences, there are many difficulties in deploying DL models trained by specific frameworks on various hardware, which promotes the research and development of DL...

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
IPC IPC(8): G06F11/36G06F8/41G06N3/04G06N5/04
CPCG06F11/3672G06F8/41G06N3/04G06N5/04
Inventor 房春荣曹可凡刘佳玮
Owner 深圳慕智科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap