<abstract xmlns="http://www.w3.org/1999/xhtml">
<p>With the widespread of systems incorporating multiple deep learning models, ensuring interoperability between target models has become essential. However, due to the unreliable performance of existing model conversion solutions, it is still challenging to ensure interoperability between the models developed on different deep learning frameworks. In this paper, we propose a systematic method for verifying interoperability between pre- and post-conversion deep learning models based on the validation and verification approach. Our proposed method ensures interoperability by conducting a series of systematic verifications from multiple perspectives. The case study confirmed that our method successfully discovered the interoperability issues that have been reported in deep learning model conversions.</p>
</abstract>

With the widespread of systems incorporating multiple deep learning models, ensuring interoperability between target models has become essential. However, due to the unreliable performance of existing model conversion solutions, it is still challenging to ensure interoperability between the models developed on different deep learning frameworks. In this paper, we propose a systematic method for verifying interoperability between pre- and post-conversion deep learning models based on the validation and verification approach. Our proposed method ensures interoperability by conducting a series of systematic verifications from multiple perspectives. The case study confirmed that our method successfully discovered the interoperability issues that have been reported in deep learning model conversions.

Towards Ensuring Software Interoperability Between Deep Learning Frameworks

Department of Computer Science and Artificial Intelligence

Journal of Artificial Intelligence and Soft Computing Research

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

{"article-title":"Towards Ensuring Software Interoperability Between Deep Learning Frameworks"}

With the widespread of systems incorporating multiple deep learning models, ensuring interoperability between target models has become essential. However, due...

Towards Ensuring Software Interoperability Between Deep Learning Frameworks

Online veröffentlicht: 30. Okt. 2023

Seitenbereich: 215 - 228

Eingereicht: 26. Juni 2023

Akzeptiert: 11. Sept. 2023

DOI: https://doi.org/10.2478/jaiscr-2023-0016

Schlüsselwörter
deep learning, interoperability, validation&verification, deep learning frameworks, model conversion

© 2023 Youn Kyu Lee et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Towards Ensuring Software Interoperability Between Deep Learning Frameworks

Online veröffentlicht: 30. Okt. 2023

Seitenbereich: 215 - 228

Eingereicht: 26. Juni 2023

Akzeptiert: 11. Sept. 2023

DOI: https://doi.org/10.2478/jaiscr-2023-0016

Schlüsselwörterdeep learning, interoperability, validation&verification, deep learning frameworks, model conversion

© 2023 Youn Kyu Lee et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Schlüsselwörter
deep learning, interoperability, validation&verification, deep learning frameworks, model conversion