Replaced KL divergence estimation with deterministic KL

[nmichlo]

What does this PR do?

Changed the VAE to compute the KL divergence directly during training, instead of estimating it by sampling from the posterior and prior distributions.

Fixes #565

Before submitting

• Was this discussed/approved via a Github issue? (no need for typos and docs improvements)
• Did you read the contributor guideline, Pull Request section?
• Did you make sure your PR does only one thing, instead of bundling different changes together?
• Did you make sure to update the documentation with your changes?
• Did you write any new necessary tests? [not needed for typos/docs]
• Did you verify new and existing tests pass locally with your changes? (I struggled to get them to run)
• If you made a notable change (that affects users), did you update the CHANGELOG?

PR review

• Is this pull request ready for review? (if not, please submit in draft mode)

Anyone in the community is free to review the PR once the tests have passed.
If we didn't discuss your PR in Github issues there's a high chance it will not be merged.