Cross-Framework Validation of CNN Architectures: From PyTorch to ONNX

Author

Shreya Nandanwar, Florida Institute of TechnologyFollow

Date of Award

5-2024

Document Type

Thesis

Degree Name

Master of Science (MS)

Department

Electrical Engineering and Computer Science

First Advisor

Siddhartha Bhattacharyya

Second Advisor

Xianqi Li

Third Advisor

Philip J. Bernhard

Fourth Advisor

Brian Lail

Abstract

This research presents CIPAC (CNN Inter-framework Parameter Analysis and Comparison), a validation approach designed to ensure the integrity of Deep Learning models during their transfer between computational frameworks. Although initially tested on Convolutional Neural Networks (CNNs), CIPAC is versatile enough for various Deep Learning architectures. It goes beyond traditional methods that focus on output accuracy, by examining the models’ architecture, parameters, and components to maintain consistency after transitions, like moving from PyTorch to ONNX framework. Inspired by software architecture’s stringent validation standards, CIPAC addresses the challenges of working with Machine Learning models on different platforms, making it an essential tool for both researchers and professionals in artificial intelligence.

Comments

Copyright held by author

Recommended Citation

Nandanwar, Shreya, "Cross-Framework Validation of CNN Architectures: From PyTorch to ONNX" (2024). Theses and Dissertations. 1443.
https://repository.fit.edu/etd/1443