tf.random.normal
Stay organized with collections
Save and categorize content based on your preferences.
Outputs random values from a normal distribution.
tf.random.normal(
shape,
mean=0.0,
stddev=1.0,
dtype=tf.dtypes.float32,
seed=None,
name=None
)
Used in the notebooks
| Used in the guide |
Used in the tutorials |
|
|
|
Example that generates a new set of random values every time:
tf.random.set_seed(5);
tf.random.normal([4], 0, 1, tf.float32)
<tf.Tensor: shape=(4,), dtype=float32, numpy=..., dtype=float32)>
Example that outputs a reproducible result:
tf.random.set_seed(5);
tf.random.normal([2,2], 0, 1, tf.float32, seed=1)
<tf.Tensor: shape=(2, 2), dtype=float32, numpy=
array([[-1.3768897 , -0.01258316],
[-0.169515 , 1.0824056 ]], dtype=float32)>
In this case, we are setting both the global and operation-level seed to
ensure this result is reproducible. See tf.random.set_seed for more
information.
Args |
|---|
shape
|
A 1-D integer Tensor or Python array. The shape of the output tensor.
|
mean
|
A Tensor or Python value of type dtype, broadcastable with stddev.
The mean of the normal distribution.
|
stddev
|
A Tensor or Python value of type dtype, broadcastable with mean.
The standard deviation of the normal distribution.
|
dtype
|
The float type of the output: float16, bfloat16, float32,
float64. Defaults to float32.
|
seed
|
A Python integer. Used to create a random seed for the distribution.
See
tf.random.set_seed
for behavior.
|
name
|
A name for the operation (optional).
|
Returns |
|---|
|
A tensor of the specified shape filled with random normal 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 2024-04-26 UTC.
[null,null,["Last updated 2024-04-26 UTC."],[],[],null,["# tf.random.normal\n\n\u003cbr /\u003e\n\n|----------------------------------------------------------------------------------------------------------------------------|\n| [View source on GitHub](https://github.com/tensorflow/tensorflow/blob/v2.16.1/tensorflow/python/ops/random_ops.py#L39-L95) |\n\nOutputs random values from a normal distribution.\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.random.normal`](https://www.tensorflow.org/api_docs/python/tf/random/normal), [`tf.compat.v1.random_normal`](https://www.tensorflow.org/api_docs/python/tf/random/normal)\n\n\u003cbr /\u003e\n\n tf.random.normal(\n shape,\n mean=0.0,\n stddev=1.0,\n dtype=../../tf/dtypes#float32,\n seed=None,\n name=None\n )\n\n### Used in the notebooks\n\n| Used in the guide | Used in the tutorials |\n|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| - [Use TF1.x models in TF2 workflows](https://www.tensorflow.org/guide/migrate/model_mapping) - [Advanced automatic differentiation](https://www.tensorflow.org/guide/advanced_autodiff) - [Introduction to modules, layers, and models](https://www.tensorflow.org/guide/intro_to_modules) - [Introduction to gradients and automatic differentiation](https://www.tensorflow.org/guide/autodiff) - [Basic training loops](https://www.tensorflow.org/guide/basic_training_loops) | - [Convolutional Variational Autoencoder](https://www.tensorflow.org/tutorials/generative/cvae) - [Deep Convolutional Generative Adversarial Network](https://www.tensorflow.org/tutorials/generative/dcgan) - [Intro to Autoencoders](https://www.tensorflow.org/tutorials/generative/autoencoder) - [Uncertainty-aware Deep Learning with SNGP](https://www.tensorflow.org/tutorials/understanding/sngp) - [Transfer learning for video classification with MoViNet](https://www.tensorflow.org/tutorials/video/transfer_learning_with_movinet) |\n\nExample that generates a new set of random values every time: \n\n tf.random.set_seed(5);\n tf.random.normal([4], 0, 1, tf.float32)\n \u003ctf.Tensor: shape=(4,), dtype=float32, numpy=..., dtype=float32)\u003e\n\nExample that outputs a reproducible result: \n\n tf.random.set_seed(5);\n tf.random.normal([2,2], 0, 1, tf.float32, seed=1)\n \u003ctf.Tensor: shape=(2, 2), dtype=float32, numpy=\n array([[-1.3768897 , -0.01258316],\n [-0.169515 , 1.0824056 ]], dtype=float32)\u003e\n\nIn this case, we are setting both the global and operation-level seed to\nensure this result is reproducible. See [`tf.random.set_seed`](../../tf/random/set_seed) for more\ninformation.\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Args ---- ||\n|----------|-----------------------------------------------------------------------------------------------------------------------------------------|\n| `shape` | A 1-D integer Tensor or Python array. The shape of the output tensor. |\n| `mean` | A Tensor or Python value of type `dtype`, broadcastable with `stddev`. The mean of the normal distribution. |\n| `stddev` | A Tensor or Python value of type `dtype`, broadcastable with `mean`. The standard deviation of the normal distribution. |\n| `dtype` | The float type of the output: `float16`, `bfloat16`, `float32`, `float64`. Defaults to `float32`. |\n| `seed` | A Python integer. Used to create a random seed for the distribution. See [`tf.random.set_seed`](../../tf/random/set_seed) for behavior. |\n| `name` | A name for the operation (optional). |\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Returns ------- ||\n|---|---|\n| A tensor of the specified shape filled with random normal values. ||\n\n\u003cbr /\u003e"]]
View source on GitHub