You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
The code in _glm_predictive_samples always applies torch.softmax to the results under classification.
For numerical stability supporting torch.log_softmax here would be helpful. Similarly, it would be helpful if there was an easy way to obtain the logits without having to change self.likelihood intermittently.
Thanks,
Andreas
The text was updated successfully, but these errors were encountered:
The code in
_glm_predictive_samples
always appliestorch.softmax
to the results under classification.For numerical stability supporting
torch.log_softmax
here would be helpful. Similarly, it would be helpful if there was an easy way to obtain the logits without having to change self.likelihood intermittently.Thanks,
Andreas
The text was updated successfully, but these errors were encountered: