Open vitkl opened 3 years ago
A related warning:
/Users/vk7/anaconda3/envs/scvi-tools-dev/lib/python3.7/site-packages/pytorch_lightning/utilities/distributed.py:69: UserWarning: you passed in a val_dataloader but have no validation_step. Skipping val loop
warnings.warn(*args, **kwargs)
We need to add a function to this class
with this signature
that
evaluate_loss
and then self.log(..)
it, or That sums over the accumulation of the loss. This would be analogous to what we discussed with averaging/summing during minibatching
Would be great to have validation set ELBO loss for pyro models. As discussed with Adam here https://github.com/YosefLab/scvi-tools/pull/1059#discussion_r633935024 @adamgayoso I can implement this, but could you point me where this belongs?