search

MIC-DKFZ / BraTS2017

Apache License 2.0
74 stars 16 forks source link

Why are convolution layer and nonlinear layer seperate? #22

Closed yianzhongguo closed 5 years ago

yianzhongguo commented 5 years ago

@FabianIsensee Hi, sir. I notice that in the design of network architecture the convolution and the nonlinear are seperate like this: l = NonlinearityLayer(l_in, nonlin), Conv3DLayer(l, feat_out, filter_size, stride, 'same', nonlinearity=linear, W=HeNormal(gain='relu')). In the Conv3DLayer the nonlinearity is set linear. What is the reason? Thank you!

yianzhongguo commented 5 years ago

I find the reason is so clear.