Justus Schock

I agree that this might be good to have, but I would not add this feature to the general engine, but maybe derive a subclass for this. Maybe we can...

How should the resulting batches look there? if you provide something like `trainer.run({"supervised": sup_dataloader, "unsupervised": unsup_dataloader}, max_epochs=10, epoch_length=len(sup_dataloader))` will you get something like ```python { 'supervised': #whatever format the supervised...

You can do this, but the prediction script was written to calculate precision and accuracy scores. Therefore you always need a ground truth. You can, however, copy the script and...

Hi, Unfortunately I cannot do this (since for thermal images I only got weights for a more advanced, internal but not yet published, method) . But it has been trained...

Hi, No the weights are still not available and I probably won't put them online in the future as well. I think the values of the Helen config file should...

no, we didn't. The thermal DB also follows the ljson standard from Menpo and was loaded using this code: https://github.com/justusschock/shapedata/blob/master/shapedata/io.py#L54 (which is also taken from Menpo/ibug)

Currently the docs are not correctly deployed on our project github page

Any opinions, on what to pass which way @delira-dev/delira ? I would prefer to expose as many options as possible and giving them good defaults, but things like loss functions,...

You got the job :D

So to summarize this: # Init: * model_cls * name * save_path * logging_type * logging_kwargs * convert_to_npy * key_mapping * verbose # train/resume/kfold: * params * val_score_key * optim_builder...