issue with dropout for the inference

Question

issue with dropout for the inference

thiravet opened this issue 4 years ago · 1 comments

Hi,

it's a nice and interesting work. But I have a question.

It seems the dropout probability stays at 0.5 for different layers (default value) for the inference with DEMO option (and not only for the training) . Is is normal or did I make a mistake?

Thanks in advance for the answer.

Answer 1 · 2021-05-31T10:03:01.000Z

sorry i didn't have the use of pytorch , i forgot to apply eval() to have the model in inference mode.