The repository contains the implementation of the Capsnet Paper
#Dynamic Routing Between Capsules - PyTorch implementation PyTorch implementation of NIPS 2017 paper Dynamic Routing Between Capsules from Sara Sabour, Nicholas Frosst and Geoffrey E. Hinton.
#Results The network trained with reconstruction and 3 routing iterations on MNIST dataset achieves 99.65% accuracy on test set. The test loss is still slightly decreasing, so the accuracy could probably be improved with more training and more careful learning rate schedule.