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

How to optimize? #1

Open
qinhaifangpku opened this issue May 29, 2018 · 1 comment
Open

How to optimize? #1

qinhaifangpku opened this issue May 29, 2018 · 1 comment

Comments

@qinhaifangpku
Copy link

hi~
Thanks for your repository!
I construct a autoencoder for CT image. I use the loss function called SigmoidCrossEntropyLoss in Caffe.
Then I got loss about 500k. It is impossoble to optimize then. My image size is about 6412896
So I want to ask for some advise from you!
Thank you in advance!

@laurahanu
Copy link
Owner

Hey!
Don't know if this is going to help, but one thing I found useful in the beginning was to start with really small images (e.g. 28x28) and troubleshoot from there! Definitely saves time if the network is not doing what it's supposed to do.. Then if you see it starts to do something sensible, you can resize your images to whatever size you want :)!

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

2 participants