Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

What is training on patchCore? (I think that patchCore does not have training phase) #52

Open
edwardcho opened this issue Sep 28, 2022 · 3 comments

Comments

@edwardcho
Copy link

Hello Sir.

I have interesting anomaly detection.
I found your code in paperwithcode, I want to try to test your code.

I think that patchCore does not have training-phase (Neural Networks) as PaDiM.
But your code has training-phase.

What is this??

Thanks,
Edward Cho.

@hcw-00
Copy link
Owner

hcw-00 commented Sep 28, 2022

Hi~
Yes. PatchCore does not need a training.
In the code it just extract features and does not update parameters.
The term "train" is just part of methods name predefined by pytorch-lightning.

@edwardcho
Copy link
Author

Hello Sir,

Thank your for your reply quickly.

But I confuse that I saw "num_epochs" in Input-parameters.
You did set that "num_epochs" : 1 only,
If I do change this value (ex: num_epochs : 100), what happened ?? is this not correct??

Thanks,
Edward Cho.

@Leonardo0325
Copy link

Leonardo0325 commented Oct 23, 2022

@edwardcho It will be very slow until crashes

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants