Examples: Quick Start

Let’s look at some examples of how easy Kur makes state-of-the-art deep learning.

Note

In this section you can jump right in and train instantly without knowing what is REALLY going on. That’s totally ok! Get hyped on Kur with the quick (and impressive) examples, then proceed to the Examples: In Depth for a more thorough going through.

First, you need to Installing Kur! If you installed via pip, you’ll need to checkout the examples directory from the repository, like this:

git clone https://github.com/deepgram/kur
cd kur/examples

If you installed via git, then you alreay have the examples directory locally, so just move into the example directory:

$ cd examples

MNIST: Handwriting recognition

Train the model on the MNIST dataset.

kur train mnist.yml

Again, evaluation is just as simple:

kur evaluate mnist.yml

CIFAR-10: Image Classification

Great, we now have a simple, but powerful and general model. Let’s train it. As before, you’ll need to cd examples first.

kur train cifar.yml

Again, evaluation is just as simple:

kur evaluate cifar.yml

DEEPGRAM10: Speech Recognition

This is the speech example with CNN layer and RNN stack.

kur train speech.yml

Again, evaluation is just as simple:

kur evaluate speech.yml