jiachengyu c8f9f5280b | 1 year ago | |
---|---|---|
.. | ||
round1 | 1 year ago | |
round2 | 1 year ago | |
round3 | 1 year ago | |
round4 | 1 year ago | |
README.md | 1 year ago |
In this folder, we upload the TrojAI competition submission code for each round.
Round 1 code is the submission for 20200725T153001 of Perspecta team. This submission has 0.30 cross entropy and 0.91 roc-auc on test set and 0.281 cross entropy loss and 0.92 roc-auc on holdout set.
Round 2 code is the submission for 20201025T122002 of Perspecta-PurdueRutgers team. This submission has 0.32 cross entropy and 0.89 roc-auc on test set and 0.38 cross entropy loss and 0.87 roc-auc on holdout set.
Round 3 code is the submission for 20201111T185002 of Perspecta-PurdueRutgers team. This submission has 0.32 cross entropy and 0.90 roc-auc on test set and 0.31 cross entropy loss and 0.91 roc-auc on holdout set.
Round 4 code is the submission for 20210120T222001 of Perspecta-PurdueRutgers team. This submission has 0.32 cross entropy and 0.90 roc-auc on test set and 0.34 cross entropy loss and 0.90 roc-auc on holdout set
The NLP rounds(round 5 to 7) can be accessed at https://github.com/PurduePAML/PICCOLO
Dear OpenI User
Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.
For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》