Training with mixed precision is returning NaN

[darkbobin]

Training with mixed precision is returning NaN

[plemeri]

Hi, thank you for your interest in our work. We tried using mixed_precision to speed up training, but ended up with not using it because it resulted much worse performance compared to the default setting. It was used in the early stage of our research, so we recommend not to enable it.

Thank you.

[darkbobin]

Thank you for your answer.
Any heads up on the performances of the model after conversion into fp16 after training though ?

[plemeri]

We're planning to release a ONNX runtime for our command-line tool / python API transparent-background powered by our InSPyReNet. Stay tuned for the updates!