This PR removes the need of torch dependency for prediction, as it uses numpy instead.
Declaring a self.device with cuda would lead to the attempt on loading torch on pickle load, which throws an error should it not be installed.
Related Issues
Checklist:
[ ] I have added tests.
[ ] I have updated the documentation accordingly.
[ ] I have updated README.md (if you are adding a new model).
[ ] I have updated examples/README.md (if you are adding a new example).
[ ] I have updated datasets/README.md (if you are adding a new dataset).
Description
This PR removes the need of
torch
dependency for prediction, as it uses numpy instead. Declaring aself.device
with cuda would lead to the attempt on loading torch on pickle load, which throws an error should it not be installed.Related Issues
Checklist:
README.md
(if you are adding a new model).examples/README.md
(if you are adding a new example).datasets/README.md
(if you are adding a new dataset).