tf.keras.utils.to_ordinal
Stay organized with collections
Save and categorize content based on your preferences.
Converts a class vector (integers) to an ordinal regression matrix.
tf.keras.utils.to_ordinal(
y, num_classes=None, dtype='float32'
)
This utility encodes class vector to ordinal regression/classification
matrix where each sample is indicated by a row and rank of that sample is
indicated by number of ones in that row.
Args |
|---|
y
|
Array-like with class values to be converted into a matrix
(integers from 0 to num_classes - 1).
|
num_classes
|
Total number of classes. If None, this would be inferred
as max(y) + 1.
|
dtype
|
The data type expected by the input. Default: 'float32'.
|
Returns |
|---|
|
An ordinal regression matrix representation of the input as a NumPy
array. The class axis is placed last.
|
Example:
a = tf.keras.utils.to_ordinal([0, 1, 2, 3], num_classes=4)
print(a)
[[0. 0. 0.]
[1. 0. 0.]
[1. 1. 0.]
[1. 1. 1.]]
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.utils.to_ordinal\n\n\u003cbr /\u003e\n\n|------------------------------------------------------------------------------------------------------------|\n| [View source on GitHub](https://github.com/keras-team/keras/tree/v2.14.0/keras/utils/np_utils.py#L80-L125) |\n\nConverts a class vector (integers) to an ordinal regression matrix. \n\n tf.keras.utils.to_ordinal(\n y, num_classes=None, dtype='float32'\n )\n\nThis utility encodes class vector to ordinal regression/classification\nmatrix where each sample is indicated by a row and rank of that sample is\nindicated by number of ones in that row.\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Args ---- ||\n|---------------|----------------------------------------------------------------------------------------------------|\n| `y` | Array-like with class values to be converted into a matrix (integers from 0 to `num_classes - 1`). |\n| `num_classes` | Total number of classes. If `None`, this would be inferred as `max(y) + 1`. |\n| `dtype` | The data type expected by the input. Default: `'float32'`. |\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Returns ------- ||\n|---|---|\n| An ordinal regression matrix representation of the input as a NumPy array. The class axis is placed last. ||\n\n\u003cbr /\u003e\n\n#### Example:\n\n a = tf.keras.utils.to_ordinal([0, 1, 2, 3], num_classes=4)\n print(a)\n [[0. 0. 0.]\n [1. 0. 0.]\n [1. 1. 0.]\n [1. 1. 1.]]"]]
View source on GitHub