Valid padding in CapNets about capsnet-tensorflow

[TarrySingh]

Hi — could you respond to the CapsLayer repo as we’ll be developing the library there :)

[phongnhhn92]

U mean I should post this question in that repo ?

[toddlt]

@phongnhhn92 I think that input of conv1 layer is MNIST image, its size is 28*28, so the output is (28-9+0*2)/1+1=20, and there are 256 neurons, so output of conv1 is (batchsize,20,20,256). The conv2 layer you said is PrimaryCaps? The vec_len of capsule is 8, so there are 8 conv layers stacked in PrimaryCaps. The output here is (20-9+2*p)/2+1=6, there are 32 neurons, each neuron calculates 8 conv, concat them will get (batchsize,6,6,32*8)