TY - GEN
T1 - A comprehensive study on challenges in deploying deep learning based software
AU - Chen, Zhenpeng
AU - Cao, Yanbin
AU - Liu, Yuanqiang
AU - Wang, Haoyu
AU - Xie, Tao
AU - Liu, Xuanzhe
N1 - Funding Information:
This work was partially supported by the Key-Area Research and Development Program of Guangdong Province under the grant number 2020B010164002, the National Natural Science Foundation of China under the grant number 61725201, and the Beijing Outstanding Young Scientist Program under the grant number BJJWZYJH01201910001004. Haoyu Wang’s work was supported by the National Natural Science Foundation of China under the grant number 61702045.
Publisher Copyright:
© 2020 ACM.
PY - 2020/11/8
Y1 - 2020/11/8
N2 - Deep learning (DL) becomes increasingly pervasive, being used in a wide range of software applications. These software applications, named as DL based software (in short as DL software), integrate DL models trained using a large data corpus with DL programs written based on DL frameworks such as TensorFlow and Keras. A DL program encodes the network structure of a desirable DL model and the process by which the model is trained using the training data. To help developers of DL software meet the new challenges posed by DL, enormous research efforts in software engineering have been devoted. Existing studies focus on the development of DL software and extensively analyze faults in DL programs. However, the deployment of DL software has not been comprehensively studied. To fill this knowledge gap, this paper presents a comprehensive study on understanding challenges in deploying DL software. We mine and analyze 3,023 relevant posts from Stack Overflow, a popular Q&A website for developers, and show the increasing popularity and high difficulty of DL software deployment among developers. We build a taxonomy of specific challenges encountered by developers in the process of DL software deployment through manual inspection of 769 sampled posts and report a series of actionable implications for researchers, developers, and DL framework vendors.
AB - Deep learning (DL) becomes increasingly pervasive, being used in a wide range of software applications. These software applications, named as DL based software (in short as DL software), integrate DL models trained using a large data corpus with DL programs written based on DL frameworks such as TensorFlow and Keras. A DL program encodes the network structure of a desirable DL model and the process by which the model is trained using the training data. To help developers of DL software meet the new challenges posed by DL, enormous research efforts in software engineering have been devoted. Existing studies focus on the development of DL software and extensively analyze faults in DL programs. However, the deployment of DL software has not been comprehensively studied. To fill this knowledge gap, this paper presents a comprehensive study on understanding challenges in deploying DL software. We mine and analyze 3,023 relevant posts from Stack Overflow, a popular Q&A website for developers, and show the increasing popularity and high difficulty of DL software deployment among developers. We build a taxonomy of specific challenges encountered by developers in the process of DL software deployment through manual inspection of 769 sampled posts and report a series of actionable implications for researchers, developers, and DL framework vendors.
KW - Deep learning
KW - Software deployment
KW - Stack Overflow
UR - http://www.scopus.com/inward/record.url?scp=85097178483&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85097178483&partnerID=8YFLogxK
U2 - 10.1145/3368089.3409759
DO - 10.1145/3368089.3409759
M3 - Conference contribution
AN - SCOPUS:85097178483
T3 - ESEC/FSE 2020 - Proceedings of the 28th ACM Joint Meeting European Software Engineering Conference and Symposium on the Foundations of Software Engineering
SP - 750
EP - 762
BT - ESEC/FSE 2020 - Proceedings of the 28th ACM Joint Meeting European Software Engineering Conference and Symposium on the Foundations of Software Engineering
A2 - Devanbu, Prem
A2 - Cohen, Myra
A2 - Zimmermann, Thomas
PB - Association for Computing Machinery, Inc
T2 - 28th ACM Joint Meeting European Software Engineering Conference and Symposium on the Foundations of Software Engineering, ESEC/FSE 2020
Y2 - 8 November 2020 through 13 November 2020
ER -