Taskonomy dataset loading

Hello,
Can you help me with **downloading** and **loading** Taskonomy dataset data?

[Download script](https://github.com/automl/NASLib/blob/Develop/naslib/data/taskonomydata_mini/download_tnb.sh) only fetches raw pixel pngs, "class_object" labels and "class_scene" labels. That only covers "autoencoder", "class_object", "class_scene" and "jigsaw" tasks. I've found that "normal" task labels can also be downloaded from downloads.cs.stanford.edu similarly to "class_object". That makes 5 out of 7 in total. How to get "room_layout" and "segmentsemantic" tasks?

When loading [TaskonomyDataset](https://github.com/automl/NASLib/blob/e7115201e2057351f165632b6ed21478323b9b74/naslib/utils/taskonomy_dataset.py#L22) it requires some json containing template paths. In loading configs (like [here](https://github.com/automl/NASLib/blob/e7115201e2057351f165632b6ed21478323b9b74/naslib/utils/dataset.py#L354)) they are marked as "final5K_splits".
How do i generate those files? I can not seem to find any scripts related to this.

Start with naslib/data/taskonomydata_mini/download_tnb.sh, naslib/utils/taskonomy_dataset.py, and the loading configuration in naslib/utils/dataset.py around the final5K_splits reference. Trace how the existing five tasks and template-path JSON files are obtained; done means the remaining task downloads and final5K_splits generation or complete instructions are documented and usable.

Written by the indexing model from the issue text.