T/SZROBOT 0004-2023
Assessment specification for deep learning model compression and quantization algorithms (English Version)

Standard No.
T/SZROBOT 0004-2023
Language
Chinese, Available in English version
Release Date
2023
Published By
Group Standards of the People's Republic of China
Latest
T/SZROBOT 0004-2023
Scope
1. Scope 2. Algorithm introduction 2.1 Multi-model compression algorithm 2.2 Quantization algorithm 2.3 Pruning algorithm 3. Terms and definitions 3.1 Reliability 3.2 Reliability evaluation 3.3 Algorithm failure 3.4 Danger 3.5 Danger severity 3.6 Precision rate 3.7 Recall rate 3.8 Accuracy Rate 3.9 Response time 3.10 Bitops 4. Evaluation index system 4.1 Evaluation index system Table 4.2 Correctness of algorithm function implementation 4.3 Performance of algorithm compression implementation 4.4 Impact of quantitative training data set 4.5 Impact of software and hardware platform dependence 4.6 Impact of environmental data 5. Evaluation process 6. Evaluation in the demand stage 7. Evaluation in the design stage 8. Evaluation in the implementation stage 9. Evaluation in the operation stage Appendix A Appendix B

T/SZROBOT 0004-2023 history

  • 2023 T/SZROBOT 0004-2023 Assessment specification for deep learning model compression and quantization algorithms



Copyright ©2024 All Rights Reserved