@inproceedings{oai:ipsj.ixsq.nii.ac.jp:00193863,
 author = {佐藤, 直人 and 來間, 啓伸 and 金子, 昌永 and 中川, 雄一郎 and 小川, 秀人 and ホン, タイソン and バトラー, マイケル and Naoto, Sato and Kuruma, Hironobu and Kaneko, Masanori and Nakagawa, Yuichiroh and Ogawa, Hideto and Thai, Son Hoang and Michael, Butler},
 book = {ウィンターワークショップ2019・イン・福島飯坂 論文集},
 month = {Jan},
 note = {In recent years, a number of methods for verifying DNNs have been developed. Because the approaches of the methods differ and have their own limitations, we think that a number of verification methods should be applied to a developed DNN. To apply a number of methods to the DNN, it is necessary to translate either the implementation of the DNN or the verification method so that one runs in the same environment as the other. Since those translations are time-consuming, a utility tool, named DeepSaucer, which helps to retain and reuse implementations of DNNs, verification methods, and their environments, is proposed. In DeepSaucer, code snippets for loading DNNs, running verification methods, and creating their environments are retained and reused as software assets in order to reduce the cost of verifying DNNs. The feasibility of DeepSaucer is confirmed by implementing it on the basis of Anaconda, which provides a virtual environment for loading a DNN and running a verification method. In addition, the effectiveness of DeepSaucer is demonstrated by an use case example., In recent years, a number of methods for verifying DNNs have been developed. Because the approaches of the methods differ and have their own limitations, we think that a number of verification methods should be applied to a developed DNN. To apply a number of methods to the DNN, it is necessary to translate either the implementation of the DNN or the verification method so that one runs in the same environment as the other. Since those translations are time-consuming, a utility tool, named DeepSaucer, which helps to retain and reuse implementations of DNNs, verification methods, and their environments, is proposed. In DeepSaucer, code snippets for loading DNNs, running verification methods, and creating their environments are retained and reused as software assets in order to reduce the cost of verifying DNNs. The feasibility of DeepSaucer is confirmed by implementing it on the basis of Anaconda, which provides a virtual environment for loading a DNN and running a verification method. In addition, the effectiveness of DeepSaucer is demonstrated by an use case example.},
 pages = {7--8},
 publisher = {情報処理学会},
 title = {DeepSaucer: Verification Environment for Deep Neural Networks},
 volume = {2019},
 year = {2019}
}