Closed ghost closed 6 years ago
https://github.com/gram-ai/capsule-networks/blob/bb65115d90da2e6313feefb529f0c159bcbcaa27/capsule_network.py#L78
If I understand correctly, squashing should be applied to the feature dimension, whereas here it seems it is applied to the capsule dimension.
Sorry, the code is not wrong. I was confused by the name of variables in the first capsule layer. In fact, the capsules and the convolutional layers are not corresponding to each other.
https://github.com/gram-ai/capsule-networks/blob/bb65115d90da2e6313feefb529f0c159bcbcaa27/capsule_network.py#L78
If I understand correctly, squashing should be applied to the feature dimension, whereas here it seems it is applied to the capsule dimension.