Details

Autor(en) / Beteiligte

• Zhang, Xiaoyu
• Zhai, Juan
• Ma, Shiqing
• Shen, Chao

Titel

AutoTrainer: An Automatic DNN Training Problem Detection and Repair System

Ist Teil von

• 2021 IEEE/ACM 43rd International Conference on Software Engineering (ICSE), 2021, p.359-371

Ort / Verlag

Piscataway, NJ, USA: IEEE Press

Erscheinungsjahr

2021

Quelle

IEEE/IET Electronic Library (IEL)

Beschreibungen/Notizen

• With machine learning models especially Deep Neural Network (DNN) models becoming an integral part of the new intelligent software, new tools to support their engineering process are in high demand. Existing DNN debugging tools are either post-training which wastes a lot of time training a buggy model and requires expertises, or limited on collecting training logs without analyzing the problem not even fixing them. In this paper, we propose AutoTrainer, a DNN training monitoring and automatic repairing tool which supports detecting and auto-repairing five commonly seen training problems. During training, it periodically checks the training status and detects potential problems. Once a problem is found, AutoTrainer tries to fix it by using built-in state-of-the-art solutions. It supports various model structures and input data types, such as Convolutional Neural Networks (CNNs) for image and Recurrent Neural Networks (RNNs) for texts. Our evaluation on 6 datasets, 495 models show that AutoTrainer can effectively detect all potential problems with 100% detection rate and no false positives. Among all models with problems, it can fix 97.33% of them, increasing the accuracy by 47.08% on average.