Update Kraków UHI dataset implementation

[wkravchyk]

What does this PR do?

This PR introduces three main updates to the Kraków UHI dataset implementation:

• update of the src/data/heat_krakow_dataset.py to the changes introduced in the PRs Organise dataset #124 and Transfer updates from BaseDataset and BaseCaption builder to the UC dataset implementations #125,
• upload of caption builder (src/data/heat_krakow_caption_builder.py) together with concept and location captions, since they were missing,
• Kraków UHI dataset model alignment config YAML files:
  • data config file: configs/data/heat_krakow_tessera_text.yaml
  • model config file: configs/model/heat_krakow_fusion_alignment.yaml,
  • experiment config file: configs/experiment/krakow/heat_krakow_alignment.yaml

Before submitting

• Did you make sure title is self-explanatory and the description concisely explains the PR?
• Did you make sure your PR does only one thing, instead of bundling different changes together?
• Did you list all the breaking changes introduced by this pull request?
• Did you test your PR locally with pytest command?

[gabrieletijunaityte]

This is only relevant to the butterfly UC, because there we obtain more data, which do not have prediction labels.

[wkravchyk]

That's clear, I added this parameter to keep compatibility with experiment tracker. It is probably better to remove it from here and replace it with **kwargs, and in config files put use_unlabelled_data: false flag.

[gabrieletijunaityte]

Yes, also you can just delete this argument from the dataset class and config file (e.g, see SatBird use case https://github.com/WUR-AI/aether/tree/train/satbird_pred )