search

naturomics / CapsNet-Tensorflow

A Tensorflow implementation of CapsNet(Capsules Net) in paper Dynamic Routing Between Capsules
Apache License 2.0
3.8k stars 1.17k forks source link

Using Caps-Net to Handle High-dimensional and Small-sample Problems #70

Open ycRose opened 6 years ago

ycRose commented 6 years ago

Hi，i'm Using Caps-Net to Handle High-dimensional and Small-sample Problems, but train cannot converge。My data dimension is 6670, 2 classes. what should i do ，thanks a lot

parinaya-007 commented 5 years ago

Can you please elaborate your problem of high dimensionality and small-sample? From what I got is that you want to know that how to converge training accuracy when input data's dimension is as big as 6670. Also do you have lesser training samples for each class? If yes, how much is it? Also if you could elaborate your network that you are currently using.