tf.keras.losses.cosine_similarity
Stay organized with collections
Save and categorize content based on your preferences.
Computes the cosine similarity between labels and predictions.
tf.keras.losses.cosine_similarity(
y_true, y_pred, axis=-1
)
Note that it is a negative quantity between -1 and 0, where 0 indicates
orthogonality and values closer to -1 indicate greater similarity. This makes
it usable as a loss function in a setting where you try to maximize the
proximity between predictions and targets.
loss = -sum(y_true * y_pred)
Args |
|---|
y_true
|
Tensor of true targets.
|
y_pred
|
Tensor of predicted targets.
|
axis
|
Axis along which to determine similarity.
|
Returns |
|---|
|
Cosine similarity tensor.
|
Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.
Last updated 2020-10-01 UTC.
[null,null,["Last updated 2020-10-01 UTC."],[],[],null,["# tf.keras.losses.cosine_similarity\n\n\u003cbr /\u003e\n\n|-----------------------------------------------------------------------------------------------------------------------------|\n| [View source on GitHub](https://github.com/tensorflow/tensorflow/blob/v2.1.0/tensorflow/python/keras/losses.py#L1064-L1093) |\n\nComputes the cosine similarity between labels and predictions.\n\n#### View aliases\n\n\n**Main aliases**\n\n[`tf.losses.cosine_similarity`](/api_docs/python/tf/keras/losses/cosine_similarity)\n**Compat aliases for migration**\n\nSee\n[Migration guide](https://www.tensorflow.org/guide/migrate) for\nmore details.\n\n[`tf.compat.v1.keras.losses.cosine`](/api_docs/python/tf/keras/losses/cosine_similarity), [`tf.compat.v1.keras.losses.cosine_proximity`](/api_docs/python/tf/keras/losses/cosine_similarity), [`tf.compat.v1.keras.losses.cosine_similarity`](/api_docs/python/tf/keras/losses/cosine_similarity), [`tf.compat.v1.keras.metrics.cosine`](/api_docs/python/tf/keras/losses/cosine_similarity), [`tf.compat.v1.keras.metrics.cosine_proximity`](/api_docs/python/tf/keras/losses/cosine_similarity)\n\n\u003cbr /\u003e\n\n tf.keras.losses.cosine_similarity(\n y_true, y_pred, axis=-1\n )\n\nNote that it is a negative quantity between -1 and 0, where 0 indicates\northogonality and values closer to -1 indicate greater similarity. This makes\nit usable as a loss function in a setting where you try to maximize the\nproximity between predictions and targets.\n\n`loss = -sum(y_true * y_pred)`\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Args ---- ||\n|----------|-------------------------------------------|\n| `y_true` | Tensor of true targets. |\n| `y_pred` | Tensor of predicted targets. |\n| `axis` | Axis along which to determine similarity. |\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Returns ------- ||\n|---|---|\n| Cosine similarity tensor. ||\n\n\u003cbr /\u003e"]]
View source on GitHub