Your Training Set is Empty

Sadly, when running ImageColorizer.ipynb I get the following message on the third step:

C:\Users\Matthew.conda\envs\deoldify\lib\site-packages\fastai\data_block.py:442: UserWarning: Your training set is empty. If this is by design, pass ignore_empty=True to remove this warning. warn(“Your training set is empty. If this is by design, pass ignore_empty=True to remove this warning.”) C:\Users\Matthew.conda\envs\deoldify\lib\site-packages\fastai\data_block.py:445: UserWarning: Your validation set is empty. If this is by design, use split_none() or pass ignore_empty=True when labelling to remove this warning. or pass ignore_empty=True when labelling to remove this warning.“”")

I am keen to see if I can download a default training set, or how to create a training set as at present I cannot use the product.

Please advise how I can overcome this issue?

Kind regards,

Matthew

[mbittraining]

Hi Jason. I really appreciate the help. Can you please set up a Teams call so that we can fix this together?

work account: [e-mail] personal: [e-mail]

Best regards,

Matthew Matthew Bennett Freelance Trainer and IT Consultant *Mbe: *07871 480008

https://www.facebook.com/mattyjbennett https://www.linkedin.com/in/matthew-bennett-a0384a11/ https://www.youtube.com/channel/UCwi6J8wbTkNQ4-wJpPS70Ug [image: Microsoft Partner - Pinpoint page]

• http://www.fsb.org.uk/*

On Thu, 9 Jul 2020 at 22:27, Jason Antic [e-mail] wrote:

@mbittraining https://github.com/mbittraining There’s two things going on here. First that’s clearly a Windows file path. Windows isn’t supported by us and you’ll likely run into issues that we won’t address here.

Second- that warning doesn’t matter in terms of inference (just colorizing images). It’ll work regardless (given you don’t have other issues running it on Windows).

I’ll commit code to silence the warning shortly just so it doesn’t cause further confusion though.

— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub https://github.com/jantic/DeOldify/issues/255#issuecomment-656359617, or unsubscribe https://github.com/notifications/unsubscribe-auth/AF4V7MU5G22HTBL4QZU5UDLR2YY3DANCNFSM4OV6DN7Q .

[mattybennett-phg]

Perfect. Thank you for your help with this, Jason. I’ll look into Deep Exemplar now.