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
Feature functionality
The idea is to introduce a function ht.unfold in the manipulations-module that has the same functionality as PyTorchs unfold.
In fact, this only requires additional efforts for the case split=dimension (dimension is the axis along which unfold takes place); otherwise you can directly apply the torch-function to the local arrays.
Hint: some auxiliary stuff required in the "difficult" case may already be implemented under the name "halo".
Additional context
With the help of such an operation it will be possible to generate sliding patches of an data set, e.g., to generate from an image (2/3d-array) the 4/5d-array of all size x size sub-images etc.
The text was updated successfully, but these errors were encountered:
Feature functionality
The idea is to introduce a function
ht.unfold
in the manipulations-module that has the same functionality as PyTorchs unfold.In fact, this only requires additional efforts for the case
split=dimension
(dimension
is the axis along which unfold takes place); otherwise you can directly apply the torch-function to the local arrays.Hint: some auxiliary stuff required in the "difficult" case may already be implemented under the name "
halo
".Additional context
With the help of such an operation it will be possible to generate sliding patches of an data set, e.g., to generate from an image (2/3d-array) the 4/5d-array of all size x size sub-images etc.
The text was updated successfully, but these errors were encountered: