wuyifan18 / DeepLog

Pytorch Implementation of DeepLog.
MIT License
372 stars 154 forks source link

Training Sequence Size #47

Closed nagsubhadeep closed 4 years ago

nagsubhadeep commented 4 years ago

Yifan,

Is there a limit to the length of the training data log sequence? Can I have a training data sequence as small as the following?

9, 7, 8 8, 9, 7, 8, 4, 7 9, 7, 6, 9, 2 . . . . 7, 8, 9, 5, 8

or a training data sequence as large as the following?

6, 8, 5, 9, 2, 9, ...... 1024 sequences 9, 8, 4, 7, 6, 1, 5, 6, 2, 9, ...... 1004 sequences . . . 6, 10, 5, 9, 3, 9, ...... 1059 sequences

In the latter case, I see that deeplog is misclassifying the sequence in most cases.

Do you know whether the number of sequences has anything to do with the classification results?

Thanks, Deep

wuyifan18 commented 4 years ago

Hi Deep, the window size, i.e., the number of sequences is a parameter, you can adjust it to achieve the best performance.

nagsubhadeep commented 4 years ago

Thanks Yifan