Need help with DeepLog?
Click the “chat” button below for chat support from the developer who created it, or find similar developers for support.

About the developer

236 Stars 123 Forks MIT License 59 Commits 20 Opened issues


Pytorch Implementation of DeepLog.

Services available


Need anything else?

Contributors list

# 142,772
55 commits


A Pytorch implementation of DeepLog's log key anomaly detection model.

If you are confusing about how to extract log key (i.e. log template), I recommend using *Drain** which is proposed in this paper. As far as I know, it is the most effective log parsing method. By the way, there is a toolkit and benchmarks for automated log parsing in this repository.*


  • python>=3.6
  • pytorch==1.4
  • tensorboard==2.0.2


~~The dataset can be downloaded HERE.~~ The website can't accessed now, but you can find the HDFS data in this repository.

The original HDFS logs can be found HERE.


Run the following code in terminal, then navigate to https://localhost:6006.

tensorboard --logdir=log


Min Du, Feifei Li, Guineng Zheng, Vivek Srikumar. "Deeplog: Anomaly detection and diagnosis from system logs through deep learning." ACM SIGSAC Conference on Computer and Communications Security(CCS), 2017.


If you have any questions, please open an issue.

Welcome to pull requests to implement the rest of this paper!

We use cookies. If you continue to browse the site, you agree to the use of cookies. For more information on our use of cookies please see our Privacy Policy.