Release for Assignment Submission

Release of codebase at time of assignment submission. Also includes collection of all tuned models as conveyed in our paper.

Tuning Results

For convenience, we provide pre-trained models in the following file:

File	Size	Description
`gan-hypertune.tar.gz`	55.6 MB (compressed), 70.8 MB (uncompressed)	Collection of all tuned models.

The tuning results consist of several files for each model:

<model>/ - Trained TensorFlow model in SavedModel format (as a directory)
<model>_hparams.json - Hyperparameter selection for model
<model>_history.csv - Training history CSV file (useful for plotting)
<model>_metrics.json - Final metric values after training (useful for tabular display)