acburigo / CapsNet

CapsNet (from "Dynamic Routing Between Capsules") implemented in pytorch.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

CapsNet

This is a pytorch implementation of CapsNet, described in the paper Dynamic Routing Between Capsules - by Sara Sabour, Nicholas Frosst and Geoffrey E Hinton.

MNIST

Accuracy

Although the paper reports an accuracy of 99.75%, the maximum accuracy achieved by this implementation was 99.68%.

Execution Speed

111 seconds per epoch on a single Titan Xp GPU.

Number of Parameters

Model has 8141840 parameters.

About

CapsNet (from "Dynamic Routing Between Capsules") implemented in pytorch.

License:MIT License


Languages

Language:Jupyter Notebook 100.0%