I have the following error:
Invalid type error in (torch.cuda.FloatTensor) while running learn.fit.
What did I do:
- downloaded Style Color images and csv file from Kaggle
- adapted the csv file a little so the first column is the Id
- used the resnet34 architecture (is the only directly available in Paperspace?)
Everything works fine until I start learn.fit and have the a.m. error.
Where to look to solve this? Thanks for your help.