RuntimeError: expected scalar type Double but found Float about cca_zoo HOT 4 CLOSED

Thanks for this! I believe I have just fixed it in latest version 1.7.10. Basically I switched the models to run double precision by default when using the DeepWrapper class (this helps with some stability issues e.g. #39). As you have noticed this wasn't compatible with the MNIST datasets which gave floats.

• I have now changed DeepWrapper to put things in double before passing to the model.
• Have also added a test that runs a subset of the tutorial to check it runs

Your comment also raised a different issue which was that the reconstruction loss in the autoencoder was reduce='sum' which is bigger with larger batch size so needs more tuning of learning rate.

• Have changed this to reduce='mean' which produces much more sensible losses and convergence for DCCAE and SplitAE

from cca_zoo.

I have uploaded a new run of the tutorial which seems to run OK so tentatively closing this but let me know if further issues

from cca_zoo.

Note - when running the notebook again you may need to run:

!pip install cca-zoo[deep,probabilistic] --upgrade

To get the new version :)

from cca_zoo.

Thank you @jameschapman19 ! That was fast! It is all working great now.
Also thank you for the AE 'reduce' parameter fix, it definitely achieves much more reasonable losses.

from cca_zoo.