Libspn-keras

What’s Changed
* Fix issues with log conv (27) jostosh

What’s Changed
- Fixes Conv2DSum forward pass
- Adds `Clip` constraint
- Adds constraint parameter to `NormalLeaf` layer
- Adds option to normalize with cross-sample statistics for `NormalizeStandardScore` layer

What’s Changed
* Add normalized greater equal epsilon constraint
* Simplify API for building random SPNs. No need to determine `factors` array for `PermuteAndPadScopesRandom` anymore when using `libspn_keras.models.SequentialSumProductNetwork`.
* Normalize EM updates and use 'gliding averages'
* Add notebook for benchmarking against Einsum Networks
* Add Dirichlet initializer for accumulators

What’s Changed

* minor fixes to actions (14) jostosh
* Add tooling and modular sum op control (13) jostosh
* Use batch first always (12) jostosh
* Feature/add accumulators location scale leafs (10) jostosh
* add image (7) jostosh
* Refactor dense ratspn (6) jostosh
* Setup, README and minor fixes (2) jostosh