Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Fix errors during training in ResponseSelector #4985

Merged
merged 13 commits into from
Dec 17, 2019
1 change: 1 addition & 0 deletions changelog/4985.bugfix.rst
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@
Set correct default value for ``dense_dim`` in ``ResponseSelector``.
2 changes: 1 addition & 1 deletion rasa/nlu/selectors/embedding_response_selector.py
Original file line number Diff line number Diff line change
Expand Up @@ -68,7 +68,7 @@ class ResponseSelector(EmbeddingIntentClassifier):
"random_seed": None,
# embedding parameters
# default dense dimension used if no dense features are present
"dense_dim": 512,
"dense_dim": {"text": 512, "intent": 20},
# dimension size of embedding vectors
"embed_dim": 20,
# the type of the similarity
Expand Down