I’m getting this warning:
/usr/local/lib/python3.8/site-packages/torch/nn/functional.py:3679: UserWarning: The default behavior for interpolate/upsample with float scale_factor changed in 1.6.0 to align with other frameworks/libraries, and now uses scale_factor directly, instead of relying on the computed output size. If you wish to restore the old behavior, please set recompute_scale_factor=True. See the documentation of nn.Upsample for details.
However, I’ve already confirmed that all of my code is using F.interpolate(input, scale_factor=(x, x)), x is just a number. I don’t know where the warning came from. Could you give me a way to better locate the issue?