Alan R Lowe

https://docs.readthedocs.io/en/stable/tutorial/index.html

https://docs.pydantic.dev/latest/usage/models/ Helps with parameter validation and serialisation.

Needs #123 Closes #36

Here: https://github.com/lowe-lab-ucl/cellx-predict/blob/9e43599973c77b436cfb637ab1dcdf68f1ce2a56/cellxpredict/train.py#L57 we should also be able to save a model (rather than just weights, since https://github.com/quantumjot/cellx/pull/44 fixed the custom layer serialization). This would make loading and inference much easier...

consider changing config dataclasses to pydantic

1

https://pydantic-docs.helpmanual.io/usage/models/

add notebook to demonstrate patch saving in tfrecord format

1

Would be good to have a notebook that takes patch images and writes them out as a tfrecord file for training the VAE.