tf.keras.backend.ndim
Stay organized with collections
Save and categorize content based on your preferences.
Returns the number of axes in a tensor, as an integer.
tf.keras.backend.ndim(
x
)
Arguments |
|---|
x
|
Tensor or variable.
|
Returns |
|---|
|
Integer (scalar), number of axes.
|
Examples:
input = tf.keras.backend.placeholder(shape=(2, 4, 5))
val = np.array([[1, 2], [3, 4]])
kvar = tf.keras.backend.variable(value=val)
tf.keras.backend.ndim(input)
3
tf.keras.backend.ndim(kvar)
2
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.backend.ndim\n\n\u003cbr /\u003e\n\n|-------------------------------------------------------------------------------|------------------------------------------------------------------------------------------------------------------------------|\n| [TensorFlow 1 version](/versions/r1.15/api_docs/python/tf/keras/backend/ndim) | [View source on GitHub](https://github.com/tensorflow/tensorflow/blob/v2.1.0/tensorflow/python/keras/backend.py#L1180-L1205) |\n\nReturns the number of axes in a tensor, as an integer.\n\n#### View aliases\n\n\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.backend.ndim`](/api_docs/python/tf/keras/backend/ndim)\n\n\u003cbr /\u003e\n\n tf.keras.backend.ndim(\n x\n )\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Arguments --------- ||\n|-----|---------------------|\n| `x` | Tensor or variable. |\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Returns ------- ||\n|---|---|\n| Integer (scalar), number of axes. ||\n\n\u003cbr /\u003e\n\n#### Examples:\n\n input = tf.keras.backend.placeholder(shape=(2, 4, 5))\n val = np.array([[1, 2], [3, 4]])\n kvar = tf.keras.backend.variable(value=val)\n tf.keras.backend.ndim(input)\n 3\n tf.keras.backend.ndim(kvar)\n 2"]]
TensorFlow 1 version
View source on GitHub