Is your squashing input dimensions correct? about capsnet-tensorflow

[naturomics]

Are you talking about this line of code?

32 is the batch size due to my GPU doesn't allow a bigger one(128 in paper). I don't know why you think it is [668, 32, 1] in the last three dims; as 1152 represents the number of capsule in the primaryCaps layer, and 8 for the length of vector s_j / v_j, where v_j is the vector output of capsule j of primaryCaps layer. In Eq. 1, || s_j || do a square norm for each v_j, where j ranges from 0 to 1152. Now, I would like to think this s_j as a vector with shape 8x1, then square_norm(s_j) = ? I think that's pretty clear.

Feel free to correct me if you believe I am wrong.

[isaacgerg]

Yes.

I was under the impression that there were 32 capsules in the network, not 1152. Is this not true?

[naturomics]

@isaacgerg Although there are not 1152 independent capsules, due to the 6x6 grid capsules share their weights, but you should count each [8,1] vector as the output of one capsule, so we have 6x6x32=1152