Softmax in routing algorithm incorrect?

[geefer]

Hi, I think the softmax in the routing algorithm is being calculated over the wrong dimension.

Currently the code has:

b_ij = Variable(torch.zeros(1, self.num_routes, self.num_capsules, 1))
       ...
        for iteration in range(num_iterations):
            c_ij = F.softmax(b_ij)

and since the dim parameter is not passed to the F.softmax call it will choose dim=1 and compute the softmax over the self.num_routes dimension (input caps or 1152 here) whereas the softmax should be computed so that the c_ij between each input capsule and all the capsules in the next layer should sum to 1.

Thus the correct call should be:

           c_ij = F.softmax(b_ij, dim=2)

[CoderHHX]

Hi, I think the softmax in the routing algorithm is being calculated over the wrong dimension.

Currently the code has:

b_ij = Variable(torch.zeros(1, self.num_routes, self.num_capsules, 1))
       ...
        for iteration in range(num_iterations):
            c_ij = F.softmax(b_ij)

and since the dim parameter is not passed to the F.softmax call it will choose dim=1 and compute the softmax over the self.num_routes dimension (input caps or 1152 here) whereas the softmax should be computed so that the c_ij between each input capsule and all the capsules in the next layer should sum to 1.

Thus the correct call should be:

           c_ij = F.softmax(b_ij, dim=2)

I agree with you that Pytorch default dim for Softmax is 1 and follow the original paper the dim should be 2.