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
In the case where the model is known and the data aren't going to be augmented,
will it be possible to pre_compute the spatial locations for the convolution, etc.. , store them with their associated data, and reload them directly during training time in order to speed up the process ?
If yes, do you have any examples ?
Best,
Thomas Chaton
The text was updated successfully, but these errors were encountered:
tchaton
changed the title
Pre_compute all the convolution possible ?
Pre_compute spatial indices for convolutions, etc .. possible ?
Feb 12, 2020
I'm working on other stuffs, so I am aiming for mid March for the release. For that, I need to implement serialization and deserialization of 1. coords key, 2. coords map, 3. coords manager, 4. and pybind11 porting all these. If you can contribute to any part of the serialization, that would be great!
Tanazzah
pushed a commit
to Tanazzah/MinkowskiEngine
that referenced
this issue
Feb 9, 2024
Dear All,
In the case where the model is known and the data aren't going to be augmented,
will it be possible to pre_compute the spatial locations for the convolution, etc.. , store them with their associated data, and reload them directly during training time in order to speed up the process ?
If yes, do you have any examples ?
Best,
Thomas Chaton
The text was updated successfully, but these errors were encountered: