experiments/STT-tensorflow
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Fixes GitHub #42458

Browse Source 
Reference PR #37905

PiperOrigin-RevId: 327372634
Change-Id: I3bdcbffca4818f62b0c5227e065f896541c6b377
This commit is contained in:
A. Unique TensorFlower 2020-08-18 22:08:10 -07:00 committed by TensorFlower Gardener
parent c82c43f658
commit 7e7641d95c
1 changed files with 7 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
tensorflow/python/keras/losses.py
View File

@ -1728,12 +1728,13 @@ def cosine_similarity(y_true, y_pred, axis=-1):
class CosineSimilarity(LossFunctionWrapper): class CosineSimilarity(LossFunctionWrapper):
"""Computes the cosine similarity between labels and predictions. """Computes the cosine similarity between labels and predictions.
Note that it is a negative quantity between -1 and 0, where 0 indicates Note that it is a number between -1 and 1. When it is a negative number
orthogonality and values closer to -1 indicate greater similarity. This makes between -1 and 0, 0 indicates orthogonality and values closer to -1
it usable as a loss function in a setting where you try to maximize the indicate greater similarity. The values closer to 1 indicate greater
proximity between predictions and targets. If either `y_true` or `y_pred` dissimilarity. This makes it usable as a loss function in a setting
is a zero vector, cosine similarity will be 0 regardless of the proximity where you try to maximize the proximity between predictions and targets.
between predictions and targets. If either `y_true` or `y_pred` is a zero vector, cosine similarity will be 0
regardless of the proximity between predictions and targets.
`loss = -sum(l2_norm(y_true) * l2_norm(y_pred))` `loss = -sum(l2_norm(y_true) * l2_norm(y_pred))`