mperezcarrasco / pytorch-dagmm Goto Github PK
View Code? Open in Web Editor NEWDeep Autoencoding Gaussian Mixture Model for Unsupervised Anomaly Detection
Deep Autoencoding Gaussian Mixture Model for Unsupervised Anomaly Detection
Hi there,
You have made a mistake in calculating the ROC_AUC in test.py line 78
print('ROC AUC score: {:.2f}'.format(roc_auc_score(labels_total, scores_total)*100))
You are including the training samples in your auc calculation. it should only include the test samples as follows
print('ROC AUC score: {:.2f}'.format(roc_auc_score(test_lables,test_energy)*100))
Thanks
Hi Manuel,
thank you for providing such a nice implementation of DAGMM for PyTorch!
While I tried out your solution, I found that the loss is not reducing and rather alternating. The original implementation in TensorFlow, however, does not have this problem.
Do you may know where this is coming from?
Best,
René
Traceback (most recent call last):
File "main.py", line 45, in
DAGMM.eval(DAGMM.model, data[1], device) # data[1]: test dataloader
AttributeError: 'TrainerDAGMM' object has no attribute 'eval'
hello, thank you for providing this code.
I can run this code, but the loss is big.etc 43425442.371?
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.