tf.keras.backend.truncated_normal
Stay organized with collections
Save and categorize content based on your preferences.
Returns a tensor with truncated random normal distribution of values.
tf.keras.backend.truncated_normal(
shape, mean=0.0, stddev=1.0, dtype=None, seed=None
)
The generated values follow a normal distribution
with specified mean and standard deviation,
except that values whose magnitude is more than
two standard deviations from the mean are dropped and re-picked.
Arguments |
shape
|
A tuple of integers, the shape of tensor to create.
|
mean
|
Mean of the values.
|
stddev
|
Standard deviation of the values.
|
dtype
|
String, dtype of returned tensor.
|
seed
|
Integer, random seed.
|
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.truncated_normal\n\n\u003cbr /\u003e\n\n|-------------------------------------------------------------------------------------------|------------------------------------------------------------------------------------------------------------------------------|\n| [TensorFlow 1 version](/versions/r1.15/api_docs/python/tf/keras/backend/truncated_normal) | [View source on GitHub](https://github.com/tensorflow/tensorflow/blob/v2.3.0/tensorflow/python/keras/backend.py#L5910-L5935) |\n\nReturns a tensor with truncated random normal distribution of values.\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.truncated_normal`](/api_docs/python/tf/keras/backend/truncated_normal)\n\n\u003cbr /\u003e\n\n tf.keras.backend.truncated_normal(\n shape, mean=0.0, stddev=1.0, dtype=None, seed=None\n )\n\nThe generated values follow a normal distribution\nwith specified mean and standard deviation,\nexcept that values whose magnitude is more than\ntwo standard deviations from the mean are dropped and re-picked.\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Arguments --------- ||\n|----------|-----------------------------------------------------|\n| `shape` | A tuple of integers, the shape of tensor to create. |\n| `mean` | Mean of the values. |\n| `stddev` | Standard deviation of the values. |\n| `dtype` | String, dtype of returned tensor. |\n| `seed` | Integer, random seed. |\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Returns ------- ||\n|---|---|\n| A tensor. ||\n\n\u003cbr /\u003e"]]