Add loss functions

[mmuckley]

This PR includes a suite of loss function refactors. Loss functions for training models are pulled out of the metrics submodule and into the new loss_fn submodule. This provides a more clear delineation of intended purpose. It also allows separate implementations, which is useful for LPIPS, where we need divide-by-0 protection for the loss, but not for the metric.

Tests are included for all metrics. The normalized LPIPS loss is tested implicitly with the MSE-LPIPS loss.

Losses include:

• Non-saturating GAN loss
• OASIS losses
• MSE loss
• MSE-LPIPS loss