This repository was archived by the owner on Nov 17, 2023. It is now read-only.
Replies: 0 comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
{{ message }}
-
I am using the mxnet-cu101mkl version. Learning is in progress with the gpu version. Inference must inevitably go with the cpu version. I want to change the model architecture trained with float32 to float16. How can I change the datatype of nn.Conv2d?
(Note that the cpu version cannot use cast.)
Beta Was this translation helpful? Give feedback.
All reactions