Yazeed Alaudah

To test trained models are saved and loaded correctly.

Currently, models that use depth in the second (Green) channel have that depth channel also visualized in Tensorboard. For better visualization, we should only show the seismic data in Tensorboard....

When running the `prepare_dutchf3.py` script, the results should be stored, and tracked, along with the outputs of each model run (logs, snapshots, configs, etc), and not separately. This means the...

In test.py, unit tests are missing for `_patch_label_2d()`. These tests will help us catch errors where predictions are all zeros or some other values.

The training scripts don't seem to support the ability to start retraining a model from a saved snapshot.