Update README.md

gorjul · web-flow · commit df940bc879b9 · 2018-10-01T16:44:42.000+02:00
diff --git a/README.md b/README.md
@@ -3,3 +3,8 @@
 As the header already tells, I used the Xception model as a base model. On top of it I inlcuded two separate output layers.
 
 The model takes one input and trains all output layers at the same time.
+
+This script was motivated by:
+
+- https://www.pyimagesearch.com/2018/06/04/keras-multiple-outputs-and-multiple-losses/
+- https://www.kaggle.com/abnera/transfer-learning-keras-xception-cnn?scriptVersionId=818701
