tf.keras.layers.maximum | TensorFlow v2.0.0 (original) (raw)
tf.keras.layers.maximum
Stay organized with collections Save and categorize content based on your preferences.
Functional interface to the Maximum layer that computes
View aliases
Compat aliases for migration
SeeMigration guide for more details.
tf.compat.v1.keras.layers.maximum
tf.keras.layers.maximum(
inputs, **kwargs
)
the maximum (element-wise) list of inputs.
For example:
input1 = tf.keras.layers.Input(shape=(16,))
x1 = tf.keras.layers.Dense(8, activation='relu')(input1) #shape=(None, 8)
input2 = tf.keras.layers.Input(shape=(32,))
x2 = tf.keras.layers.Dense(8, activation='relu')(input2) #shape=(None, 8)
max_inp=tf.keras.layers.maximum([x1,x2]) #shape=(None, 8)
out = tf.keras.layers.Dense(4)(max_inp)
model = tf.keras.models.Model(inputs=[input1, input2], outputs=out)
| Arguments | |
|---|---|
| inputs | A list of input tensors (at least 2) of same shape. |
| **kwargs | Standard layer keyword arguments. |
| Returns |
|---|
| A tensor (of same shape as input tensor) with the element-wise maximum of the inputs. |
| Raises | |
|---|---|
| ValueError | If input tensors are of different shape. |
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.