2026-04-17T12:56:55Z https://ipsj.ixsq.nii.ac.jp/oai

oai:ipsj.ixsq.nii.ac.jp:00193863 2025-01-19T23:47:46Z 6164:6165:7019:9662

DeepSaucer: Verification Environment for Deep Neural Networks DeepSaucer: Verification Environment for Deep Neural Networks 佐藤, 直人 來間, 啓伸 金子, 昌永 中川, 雄一郎 小川, 秀人 ホン, タイソン バトラー, マイケル Naoto, Sato Kuruma, Hironobu Kaneko, Masanori Nakagawa, Yuichiroh Ogawa, Hideto Thai, Son Hoang Michael, Butler 深層学習システムのテスト・検証 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. conference paper 情報処理学会 2019-01-17 application/pdf ウィンターワークショップ2019・イン・福島飯坂 論文集 2019 7 8 https://ipsj.ixsq.nii.ac.jp/record/193863/files/IPSJ-WWS2019004.pdf eng