ml-lab / capsnet-tensorflow

A Tensorflow implementation of CapsNet(Capsules Net) in Hinton's paper Dynamic Routing Between Capsules

CapsNet-Tensorflow

A Tensorflow implementation of CapsNet in Hinton's paper Dynamic Routing Between Capsules

The code is not complete yet, I'm trying to finish it as quickly as possible. Here is my understanding of the section 4 of the paper (the core part of CapsNet), it might be helpful for understanding the code. Thanks for your focus

Give me one day more, and I will move the earth. ---- Archimedes 😊

Requirements

• Python
• NumPy
• Tensorflow (I'm using 1.3.0, others should work, too)

Usage

Training

Step 1. Clone this repository with git.

$ git clone https://github.com/naturomics/CapsNet-Tensorflow.git
$ cd CapsNet-Tensorflow

Step 2. Download MNIST dataset, mv and extract them into data/mnist directory.(Be careful the backslash appeared around the curly braces when you copy the wget command to your terminal, remove it)

$ mkdir -p data/mnist
$ wget -c -P data/mnist http://yann.lecun.com/exdb/mnist/{train-images-idx3-ubyte.gz,train-labels-idx1-ubyte.gz,t10k-images-idx3-ubyte.gz,t10k-labels-idx1-ubyte.gz}
$ gunzip data/mnist/*.gz

Step 3. Start training with command line:

$ python train.py

Evaluation

$ python eval.py

Results