leftthomas / Capsnet
Licence: mit
A PyTorch implementation of CapsNet based on NIPS 2017 paper "Dynamic Routing Between Capsules"
Stars: ✭ 141
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Capsnet
Capsnet Keras
A Keras implementation of CapsNet in NIPS2017 paper "Dynamic Routing Between Capsules". Now test error ＝ 0.34%.
Stars: ✭ 2,428 (+1621.99%)
Mutual labels: capsnet
CapsNet
Empirical studies on Capsule Network representation and improvements implemented with PyTorch.
Stars: ✭ 39 (-72.34%)
Mutual labels: capsnet
capsules-tensorflow
Another implementation of Hinton's capsule networks in tensorflow.
Stars: ✭ 18 (-87.23%)
Mutual labels: capsnet
Capsnet Visualization
🎆 A visualization of the CapsNet layers to better understand how it works
Stars: ✭ 371 (+163.12%)
Mutual labels: capsnet
Capsnet Traffic Sign Classifier
A Tensorflow implementation of CapsNet(Capsules Net) apply on german traffic sign dataset
Stars: ✭ 166 (+17.73%)
Mutual labels: capsnet
Capsnet guide pytorch
A tutorial-style implementation of CapsNet in PyTorch
Stars: ✭ 104 (-26.24%)
Mutual labels: capsnet
Capsnet Pytorch
PyTorch implementation of NIPS 2017 paper Dynamic Routing Between Capsules
Stars: ✭ 440 (+212.06%)
Mutual labels: capsnet
CapsNet-tensorflow-jupyter
A simple tensorflow implementation of CapsNet (by Dr. G. Hinton), based on my understanding. This repository is built with an aim to simplify the concept, implement and understand it.
Stars: ✭ 16 (-88.65%)
Mutual labels: capsnet
Capsnet Tensorflow
A Tensorflow implementation of CapsNet(Capsules Net) in paper Dynamic Routing Between Capsules
Stars: ✭ 3,776 (+2578.01%)
Mutual labels: capsnet
CapsNet-Fashion-MNIST
Capsule Network on Fashion MNIST dataset
Stars: ✭ 93 (-34.04%)
Mutual labels: capsnet
Matrix Capsules With Em Routing
A TensorFlow implementation of "Matrix Capsules with EM Routing" by Hinton et al. (2018).
Stars: ✭ 74 (-47.52%)
Mutual labels: capsnet
Dynamic routing between capsules
Implementation of Dynamic Routing Between Capsules, Sara Sabour, Nicholas Frosst, Geoffrey E Hinton, NIPS 2017
Stars: ✭ 202 (+43.26%)
Mutual labels: capsnet
Capslayer
CapsLayer: An advanced library for capsule theory
Stars: ✭ 351 (+148.94%)
Mutual labels: capsnet
Capsule Gan
Code for my Master thesis on "Capsule Architecture as a Discriminator in Generative Adversarial Networks".
Stars: ✭ 120 (-14.89%)
Mutual labels: capsnet
Variational Capsule Routing
Official Pytorch code for (AAAI 2020) paper "Capsule Routing via Variational Bayes", https://arxiv.org/pdf/1905.11455.pdf
Stars: ✭ 84 (-40.43%)
Mutual labels: capsnet
Capsnet
CapsNet (Capsules Net) in Geoffrey E Hinton paper "Dynamic Routing Between Capsules" - State Of the Art
Stars: ✭ 423 (+200%)
Mutual labels: capsnet
CapsNet
A PyTorch implementation of CapsNet based on NIPS 2017 paper Dynamic Routing Between Capsules.
Requirements
- Anaconda
- PyTorch
conda install pytorch torchvision -c soumith
conda install pytorch torchvision cuda80 -c soumith # install it if you have installed cuda
- PyTorchNet
pip install git+https://github.com/pytorch/[email protected]
Usage
git clone https://github.com/leftthomas/CapsNet.git
cd CapsNet
python -m visdom.server & python main.py
Visdom now can be accessed by going to 127.0.0.1:8097 in your browser, or your own host address if specified.
Benchmarks
Highest accuracy was 99.57% after 30 epochs. The model may achieve a higher accuracy as shown by the trend of the loss/accuracy graphs below.
|
|
|
|
The confusion matrix of the digit numbers are showed below.
The reconstructions of the digit numbers are showed at right and the ground truth at left.
|
|
Default PyTorch Adam optimizer hyperparameters were used with no learning rate scheduling. Epochs with batch size of 100 takes ~2 minutes on a NVIDIA GTX 1070 GPU.
Other Implementations
Credits
Primarily referenced this implementation: PyTorch implementation by @Gram.AI
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].