A Tensorflow implementation of CapsNet(Capsules Net) apply on the German traffic sign dataset
This implementation is based on this paper: Dynamic Routing Between Capsules (https://arxiv.org/abs/1710.09829) from Sara Sabour, Nicholas Frosst and Geoffrey E. Hinton.
This repository is a work in progress implementation of a Capsules
Net. Since I am using a different dataset (Not MNIST) some details in
the architecture are different. The code for the CapsNet is located in
the following file: caps_net.py while the whole model is created inside the model.py file. The two main methods used to build the CapsNet are conv_caps_layer and fully_connected_caps_layer
During the training, the checkpoint is saved by default into the
outputs/checkpoints/ folder. The exact path and name of the checkpoint
is print during the training.
Test
In order to measure the accuracy and the loss on the Test dataset you need to used the test.py script as follow: