Ever wanted to use weights of your previous model to initialize you new model? But here's the catch: you can't do this
if the layer's shape has changed. keras_warmstarter reshape the kernel such that the new layer compute a function
which is close to the old layer.
-
Notifications
You must be signed in to change notification settings - Fork 0
thib-s/keras_warmstarter
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
Allow you to initialize the weights of a model, by reusing to weights of a previous model.
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published