search

automl / TabPFN

Official implementation of the TabPFN paper (https://arxiv.org/abs/2207.01848) and the tabpfn package.
http://priorlabs.ai
Apache License 2.0
1.22k stars 109 forks source link

TabPFNClassifier.predict raise torch warning #60

Closed G-Piotr closed 1 year ago

G-Piotr commented 1 year ago

classifier.predict results in: _Lib\site-packages\torch\utils\checkpoint.py:429: UserWarning: torch.utils.checkpoint: please pass in use_reentrant=True or use_reentrant=False explicitly. The default value of use_reentrant will be updated to be False in the future. To maintain current behavior, pass use_reentrant=True. It is recommended that you use usereentrant=False. Refer to docs for more details on the differences between the two variants. warnings.warn(

where classifier = TabPFNClassifier(device='cpu', N_ensemble_configurations=32) torch version '2.1.0+cpu' for current TabPFN

noahho commented 1 year ago

This shouldn't change behavior, but you can catch warning if you like to (https://stackoverflow.com/questions/5644836/in-python-how-does-one-catch-warnings-as-if-they-were-exceptions) Correct torch version would be 1.9, thats why youre getting this warning, but as I said probably you don't need to worry.