tf.nn.softmax | TensorFlow v2.16.1 (original) (raw)

tf.nn.softmax

Stay organized with collections Save and categorize content based on your preferences.

Computes softmax activations.

View aliases

Main aliases

tf.math.softmax

tf.nn.softmax(
    logits, axis=None, name=None
)

Used in the notebooks

Used in the guide	Used in the tutorials
Multilayer perceptrons for digit recognition with Core APIs TensorFlow basics Introduction to Tensors Training & evaluation with the built-in methods	Uncertainty-aware Deep Learning with SNGP Integrated gradients Custom training: walkthrough Image classification Simple audio recognition: Recognizing keywords

Used for multi-class predictions. The sum of all outputs generated by softmax is 1.

This function performs the equivalent of

softmax = tf.exp(logits) / tf.reduce_sum(tf.exp(logits), axis, keepdims=True)

Example usage:

softmax = tf.nn.softmax([-1, 0., 1.]) softmax <tf.Tensor: shape=(3,), dtype=float32, numpy=array([0.09003057, 0.24472848, 0.66524094], dtype=float32)> sum(softmax) <tf.Tensor: shape=(), dtype=float32, numpy=1.0>

Args
logits	A non-empty Tensor. Must be one of the following types: half,float32, float64.
axis	The dimension softmax would be performed on. The default is -1 which indicates the last dimension.
name	A name for the operation (optional).

Returns
A Tensor. Has the same type and shape as logits.

Raises
InvalidArgumentError	if logits is empty or axis is beyond the last dimension of logits.

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.