You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
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!
The text was updated successfully, but these errors were encountered:
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 :)!
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!
The text was updated successfully, but these errors were encountered: