An implementation of the Kohonen self-organizing map1 for TensorFlow 1.5 and Python 3.6. This was initially based off of Sachin Joglekar's code but has a few key modifications:
- Uses TensorFlow broadcasting semantics instead of
tf.packandforloops. - Input data is expected from a
Tensorrather than atf.placeholder, allowing for use with faster and more complex input data pipelines. - Training uses the batch algorithm rather than the online one, providing a major speed boost if you have the GPU RAM. Also, as a result of that, I added...
- Multi-GPU support (for single machines with multiple GPUs, it doesn't have multi-node training).
- Some summary operations for Tensorboard visualization
example.py contains a simple example of its usage by training a SOM on a 3 cluster toy dataset. The resulting
u-matrix should look something like this:
I was going to write a blog post about this but I ended up just repeating everything I wrote in the comments, so please read them if you'd like to understand the code. For reference, the batch formula for SOMs is
where theta is the neighborhood function and x is the input vector.