Deep Embedding Clustering (DEC) in Tensorflow

Tensorflow implementation of Unsupervised Deep Embedding for Clustering Analysis.

Installation

>>> pip3 install -r requirements.txt

Training

usage: train.py [-h] [--batch-size BATCH_SIZE] [--gpu-index GPU_INDEX]

optional arguments:
  -h, --help            show this help message and exit
  --batch-size BATCH_SIZE
                        Train Batch Size
  --gpu-index GPU_INDEX
                        GPU Index Number

Visualize

The inference.py returns the latent representation ($z$), and exports the z.tsv, meta.tsv (label information).

usage: inference.py [-h] [--gpu-index GPU_INDEX]

optional arguments:
  -h, --help            show this help message and exit
  --gpu-index GPU_INDEX
                        GPU Index Number

For visualization, we use t-SNE by importing z.tsv, meta.tsv into Tensorboard. The visualization using MNIST shows as follow.