Fault Localization for Buggy Deep Learning Framework Conversions in Image Recognition

arXiv:2306.06157v5 Announce Type: replace-cross
Abstract: When deploying Deep Neural Networks (DNNs), developers often convert models from one deep learning framework to another (e.g., TensorFlow to PyTorch). However, this process is error-prone and can impact target model accuracy. To identify the extent of such impact, we perform and briefly present a differential analysis against three DNNs widely used for image recognition (MobileNetV2, ResNet101, and InceptionV3) converted across four well-known deep learning frameworks (PyTorch, Keras, TensorFlow (TF), and TFLite), which revealed numerous …

abstract accuracy arxiv cs.cv cs.lg cs.se cs.sy deep learning deep learning framework developers eess.sy error framework however identify image image recognition impact localization model accuracy networks neural networks process pytorch recognition tensorflow type