tf.keras.metrics.categorical_accuracy
Stay organized with collections
Save and categorize content based on your preferences.
Calculates how often predictions match one-hot labels.
tf.keras.metrics.categorical_accuracy(
y_true, y_pred
)
Standalone usage:
y_true = [[0, 0, 1], [0, 1, 0]]
y_pred = [[0.1, 0.9, 0.8], [0.05, 0.95, 0]]
m = tf.keras.metrics.categorical_accuracy(y_true, y_pred)
assert m.shape == (2,)
m.numpy()
array([0., 1.], dtype=float32)
You can provide logits of classes as y_pred, since argmax of
logits and probabilities are same.
Args |
|---|
y_true
|
One-hot ground truth values.
|
y_pred
|
The prediction values.
|
Returns |
|---|
|
Categorical accuracy values.
|
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. Some content is licensed under the numpy license.
Last updated 2023-10-06 UTC.
[null,null,["Last updated 2023-10-06 UTC."],[],[],null,["# tf.keras.metrics.categorical_accuracy\n\n\u003cbr /\u003e\n\n|-----------------------------------------------------------------------------------------------------------------------|\n| [View source on GitHub](https://github.com/keras-team/keras/tree/v2.13.1/keras/metrics/accuracy_metrics.py#L399-L428) |\n\nCalculates how often predictions match one-hot labels.\n\n#### View aliases\n\n\n**Main aliases**\n\n[`tf.metrics.categorical_accuracy`](https://www.tensorflow.org/api_docs/python/tf/keras/metrics/categorical_accuracy)\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.metrics.categorical_accuracy\\`\n\n\u003cbr /\u003e\n\n tf.keras.metrics.categorical_accuracy(\n y_true, y_pred\n )\n\n#### Standalone usage:\n\n y_true = [[0, 0, 1], [0, 1, 0]]\n y_pred = [[0.1, 0.9, 0.8], [0.05, 0.95, 0]]\n m = tf.keras.metrics.categorical_accuracy(y_true, y_pred)\n assert m.shape == (2,)\n m.numpy()\n array([0., 1.], dtype=float32)\n\nYou can provide logits of classes as `y_pred`, since argmax of\nlogits and probabilities are same.\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Args ---- ||\n|----------|------------------------------|\n| `y_true` | One-hot ground truth values. |\n| `y_pred` | The prediction values. |\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Returns ------- ||\n|---|---|\n| Categorical accuracy values. ||\n\n\u003cbr /\u003e"]]
View source on GitHub