PyTorch fails on me when using local Jupyter to run epochs

vision
1

Hi.

I am trying to run a classifier on my local notebook to use my own GPU instead of relying on Colab. When I try to run a single epoch to find the learning rate, I get this many repeats of this message:

/home/onur/.local/lib/python3.6/site-packages/torch/nn/functional.py:2854: UserWarning: The default behavior for interpolate/upsample with float scale_factor will change in 1.6.0 to align with other frameworks/libraries, and use scale_factor directly, instead of relying on the computed output size. If you wish to keep the old behavior, please set recompute_scale_factor=True. See the documentation of nn.Upsample for details.

I get that its just a warning but my epoch does not run at all.

2

Are you able to train when you set recompute_scale_factor=True?

3

Where do I set that and what is its significance?

4

It doesn’t solve the problem