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
Currently users can use standard Xavier etc initialization, which as it stands seems to use fanIn == vocabSize, which results in very small initializations.
This should be checked, and a better scheme implemented (maybe treat fanIn as 1, or warn the user or something)
The text was updated successfully, but these errors were encountered:
* deeplearning4j#8565 Normalizer toString/hashcode
Signed-off-by: Alex Black <blacka101@gmail.com>
* deeplearning4j#8731 ImagePreProcessingScaler lables/segmentation fix
Signed-off-by: Alex Black <blacka101@gmail.com>
* deeplearning4j#8691 Fix SameDiffLayer/Vertx finetuning and parameter setting support
Signed-off-by: Alex Black <blacka101@gmail.com>
* deeplearning4j#8663 DL4J embedding layer weight init - don't depend on vocab size
Signed-off-by: Alex Black <blacka101@gmail.com>
* EmbeddingLayer test tweak
Signed-off-by: Alex Black <blacka101@gmail.com>
Currently users can use standard Xavier etc initialization, which as it stands seems to use fanIn == vocabSize, which results in very small initializations.
This should be checked, and a better scheme implemented (maybe treat fanIn as 1, or warn the user or something)
The text was updated successfully, but these errors were encountered: