You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
This question is independent of ENet but rather a general question. Did you ask this on caffe-users as well?
I think in general this should be possible. However, this does not speed up the network, because caffe-enet does not support fp16 operations.
The Caffe framework from Nvidia supports fp16 operations: https://github.com/NVIDIA/caffe
If you like to use ENet with fp16, you have to make all necessary modifications to the NVIDIA/caffe, which were done at caffe-enet.
Is it possible to convert a pre-trained ENet into a half-precision version?
Thanks
The text was updated successfully, but these errors were encountered: