Fix-Con: Automatic Fault Localization and Repair of Deep Learning Model Conversions

Converting deep learning models between frameworks is a common step to maximize model compatibility across devices and leverage optimization features that may be exclusively provided in one deep learning framework. However, this conversion process may be riddled with bugs, making the converted models either undeployable or problematic, considerably degrading their prediction correctness.
We propose an automated approach for fault localization and repair, Fix-Con, during model conversion between deep learning frameworks. Fix-Con is capable of detecting and fixing faults introduced in …

bugs conversion cs.ai cs.cv cs.lg cs.se deep learning deep learning framework devices features framework frameworks localization making optimization process