0hY zdZddlmcmZddlmZddlmZedGddeZ edd Z y) zALayer that computes the maximum (element-wise) of several inputs.N)_Merge) keras_exportzkeras.layers.MaximumceZdZdZdZy)MaximumaLayer that computes the maximum (element-wise) a list of inputs. It takes as input a list of tensors, all of the same shape, and returns a single tensor (also of the same shape). >>> tf.keras.layers.Maximum()([np.arange(5).reshape(5, 1), ... np.arange(5, 10).reshape(5, 1)]) >>> x1 = tf.keras.layers.Dense(8)(np.arange(10).reshape(5, 2)) >>> x2 = tf.keras.layers.Dense(8)(np.arange(10, 20).reshape(5, 2)) >>> maxed = tf.keras.layers.Maximum()([x1, x2]) >>> maxed.shape TensorShape([5, 8]) cv|d}tdt|D]}tj|||}|S)Nr)rangelentfmaximum)selfinputsoutputis ]/var/www/html/engine/venv/lib/python3.12/site-packages/tf_keras/src/layers/merging/maximum.py_merge_functionzMaximum._merge_function1s>q#f+& 3AZZq 2F 3 N)__name__ __module__ __qualname____doc__rrrrrs *rrzkeras.layers.maximumc $tdi||S)aFunctional interface to compute maximum (element-wise) list of `inputs`. This is equivalent to the `tf.keras.layers.Maximum` layer. For example: ```python 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) ``` Args: inputs: A list of input tensors 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. r)r)rkwargss rr r 8s: 7 V V $$r) rtensorflow.compat.v2compatv2r &tf_keras.src.layers.merging.base_merger tensorflow.python.util.tf_exportrrr rrrr sVH"!9:$%f&:$%%&%r