tf.math.log

Computes natural logarithm of x element-wise.

View aliases

Compat aliases for migration

tf.compat.v1.log

tf.math.log(
    x: Annotated[Any, tf.raw_ops.Any],
    name=None
) -> Annotated[Any, tf.raw_ops.Any]

Used in the notebooks

Used in the guide	Used in the tutorials
Optimizers with Core APIs	Convolutional Variational Autoencoder Playing CartPole with the Actor-Critic method Learnable Distributions Zoo Bayesian Modeling with Joint Distribution Audio Data Preparation and Augmentation

I.e., \(y = \log_e x\).

Example:

x = tf.constant([0, 0.5, 1, 5])
tf.math.log(x)
<tf.Tensor: shape=(4,), dtype=float32, numpy=array([      -inf, -0.6931472,  0.       ,  1.609438 ], dtype=float32)>

See: https://en.wikipedia.org/wiki/Logarithm

Args
`x`	A `Tensor`. Must be one of the following types: `bfloat16`, `half`, `float32`, `float64`, `complex64`, `complex128`.
`name`	A name for the operation (optional).

Returns
A `Tensor`. Has the same type as `x`.

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.

tf.math.log

View aliases

Used in the notebooks

Example:

Args

Returns