ImageDatabrunch Error Colab Lesson 1

Part 1 (2019)
1

Hello I’m starting out my fast.ai journey on colab. On Lesson 1 if I try to access
the

data = ImageDataBunch.from_name_re(path_img, fnames, pat, ds_tfms=get_transforms(), size=224, bs=bs).normalize(imagenet_stats)
it is giving me this warning. Please help as I’ve tried setting recompute_scale_factor=True part as parameter on ImageDataBrunch.

"/usr/local/lib/python3.6/dist-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. warnings.warn("The default behavior for interpolate/upsample with float scale_factor will change "

1 Like
2

I just ran into this myself.
see this thread: FastAI throwing a runtime error when using custom train & test sets

The latest pytorch version is incompatible with the current fastai libs.
There are multiple solutions; the simplest is to downgrade torch:

!pip install "torch==1.4" "torchvision==0.5.0"