learning/annotated_deep_learning_paper_implementations
1
0
Fork 0
mirror of https://github.com/labmlai/annotated_deep_learning_paper_implementations.git synced 2025-11-02 21:40:15 +08:00
Code Issues Packages Projects Releases Wiki Activity

capsule net descriptions

Browse Source
This commit is contained in:
Varuna Jayasiri
2021-01-16 20:58:25 +05:30
parent 642c944e1b
commit fb2ecb6637
2 changed files with 11 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
labml_nn/capsule_networks/__init__.py
View File

@ -2,17 +2,17 @@
--- ---
title: Capsule Networks title: Capsule Networks
summary: > summary: >
PyTorch implementation/tutorial of Capsule Networks. PyTorch implementation and tutorial of Capsule Networks.
Capsule networks is neural network architecture that embeds features Capsule networks is neural network architecture that embeds features
as capsules and routes them with a voting mechanism to next layer of capsules. as capsules and routes them with a voting mechanism to next layer of capsules.
--- ---
# Capsule Networks # Capsule Networks
This is an implementation of [Dynamic Routing Between Capsules](https://arxiv.org/abs/1710.09829). This is a PyTorch implementation and tutorial of [Dynamic Routing Between Capsules](https://arxiv.org/abs/1710.09829).
Capsule networks is neural network architecture that embeds features as capsules and routes them Capsule networks is neural network architecture that embeds features
with a voting mechanism to next layer of capsules. as capsules and routes them with a voting mechanism to next layer of capsules.
Unlike in other implementations of models, we've included a sample, because Unlike in other implementations of models, we've included a sample, because
it is difficult to understand some of the concepts with just the modules. it is difficult to understand some of the concepts with just the modules.

10
labml_nn/capsule_networks/mnist.py
View File

@ -6,6 +6,8 @@ summary: Code for training Capsule Networks on MNIST dataset
# Classify MNIST digits with Capsule Networks # Classify MNIST digits with Capsule Networks
This is an annotated PyTorch code to classify MNIST digits with PyTorch.
This paper implements the experiment described in paper This paper implements the experiment described in paper
[Dynamic Routing Between Capsules](https://arxiv.org/abs/1710.09829). [Dynamic Routing Between Capsules](https://arxiv.org/abs/1710.09829).
""" """
@ -161,11 +163,13 @@ def main():
""" """
Run the experiment Run the experiment
""" """
conf = Configs()
experiment.create(name='capsule_network_mnist') experiment.create(name='capsule_network_mnist')
conf = Configs()
experiment.configs(conf, {'optimizer.optimizer': 'Adam', experiment.configs(conf, {'optimizer.optimizer': 'Adam',
'optimizer.learning_rate': 1e-3, 'optimizer.learning_rate': 1e-3})
'device.cuda_device': 1})
experiment.add_pytorch_models({'model': conf.model})
with experiment.start(): with experiment.start():
conf.run() conf.run()