How to show_results(rows, figsize) for a model trained with to_fp16()

Part 1 (2019) Advanced (Part 1 v3)
1

My learner is trained with fp16
I run

learner.show_results(rows=3, figsize=(8,9))

to get this error:
RuntimeError: Input type (torch.cuda.FloatTensor) and weight type (torch.cuda.HalfTensor) should be the same

1 Like
2

The solution of your problem is in this post.