Lightning-AI / torchmetrics

Torchmetrics - Machine learning metrics for distributed, scalable PyTorch applications.

Home Page:https://lightning.ai/docs/torchmetrics/

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

The default value of `compute_with_cache` should be `True` .

S-aiueo32 opened this issue Β· comments

πŸ“š Documentation

I found an inconsistency around compute_with_cache in Metic.
The docstring says the default value is False but the actual one is True.

- compute_with_cache: If results from ``compute`` should be cached. Default is ``False``

self.compute_with_cache = kwargs.pop("compute_with_cache", True)

Hi! thanks for your contribution!, great first issue!

I'm ready to send PR from here.