[ENH] Loading ability in deep learning modules for classification/regression/clustering

[hadifawaz1999]

Fix #385

Deep learning base models now have a loading function to load a saved pretrained model and skip the fitting phase. This required testing the functionality in deep base, which i added.

I added a demo on how to use this functionality in the deep learning notebook examples/networks/deep_learning
I also updated some of the figures, using the new ones from here now: https://msd-irimas.github.io/pages/dl4tsc/

[review-notebook-app]

Check out this pull request on 

See visual diffs & provide feedback on Jupyter Notebooks.

---

Powered by ReviewNB

[aeon-actions-bot]

Thank you for contributing to aeon

The Checks tab will show the status of our automated tests. You can click on individual test runs in the tab or "Details" in the panel below to see more information if there is a failure.

If our pre-commit code quality check fails, any trivial fixes will automatically be pushed to your PR unless it is a draft.

Don't hesitate to ask questions on the aeon Slack channel if you have any.

[TonyBagnall]

I think you should create a temp directory to the writing and loading of files, and possibly only do it on overnight tests (although not sure about that)

this from test_data_writers.py

with tempfile.TemporaryDirectory() as tmp:
    write_to_tsfile(X=X, path=tmp, y=y, problem_name=problem_name)
    load_path = os.path.join(tmp, problem_name)
    newX, newy = load_from_tsfile(full_file_path_and_name=load_path)

[TonyBagnall]

lgtm