Lazy Reset Grad

Description

Clears the accumulated gradients in memory. This is typically done after an optimizer step to prevent reusing stale gradients in the next update.
Documentation illustration (illustration unavailable in the archive).

Input parameters

 

 Training in : object, training session.

Output parameters

 

 Training out : object, training session.

Example

All these exemples are snippets PNG, you can drop these Snippet onto the block diagram and get the depicted code added to your VI (Do not forget to install Deep Learning library to run it).