A Keras implementation of CapsNet in the paper:
Sara Sabour, Nicholas Frosst, Geoffrey E Hinton. Dynamic Routing Between Capsules. NIPS 2017
This code is adopted from CapsNet-Keras to test the performance of CapsNet on Fashion-MNIST
Contacts
Xifeng Guo
E-mail guoxifeng1990@163.com or WeChat wenlong-guo.
Step 1. Install Keras 2.0.9 with TensorFlow backend.
pip install tensorflow-gpu
pip install keras==2.0.9Step 2. Clone this repository to local.
git clone https://github.com/XifengGuo/CapsNet-Fashion-MNIST.git
cd CapsNet-Fashion-MNISTStep 3. Train a CapsNet on Fashion-MNIST
Training with default settings:
$ python capsulenet.pyData preprocessing:
[0,1]; Accuracy
Test Accuracy: 93.62%
Losses and accuracies:
Training Speed
About 120s / epoch on a single GTX 1070 GPU.
Reconstruction result
Top 5 rows are real images from MNIST and Bottom are corresponding reconstructed images.
