I came across an implementation of DropConnect layer in TensorLayer: http://tensorlayer.readthedocs.io/en/latest/modules/layers.html but I need a Keras equivalent. Are there any implementations for DropConnect on Keras? If not, can any existing Keras layers be converted to DropConnect?
3 Answers
Currently there is no official Keras implementation of DropConnect layer, but you can use the implementation from this github: https://github.com/andry9454/KerasDropconnect.
There they explain how to use their code.
The DropConnect classes are in ddrop/layers.py.
So basically they've created the custom Keras Dense-layer (class that extends the Dense layer) and implements "dropping" of weights and also a custom Keras layer-wrapper which you can use.
I've used only the wrapper, I've tried the extended Dense layer but it looks like it has some fixable issues...
I'm not sure if the wrapper works for layers that aren't Dense layers, you can try it...
here is a simple way to use TensorLayer and Keras together, so you don't need to reimplement the dropconnect layer in Keras.
Related