View source on GitHub |
Average Pooling layer for 1D inputs.
tf.compat.v1.layers.average_pooling1d(
inputs,
pool_size,
strides,
padding='valid',
data_format='channels_last',
name=None
)
Migrate to TF2
This API is a legacy api that is only compatible with eager execution and
tf.function
if you combine it with
tf.compat.v1.keras.utils.track_tf1_style_variables
Please refer to tf.layers model mapping section of the migration guide to learn how to use your TensorFlow v1 model in TF2 with Keras.
The corresponding TensorFlow v2 layer is
tf.keras.layers.AveragePooling1D
.
Structural Mapping to Native TF2
None of the supported arguments have changed name.
Before:
y = tf.compat.v1.layers.average_pooling1d(x, pool_size=2, strides=2)
After:
To migrate code using TF1 functional layers use the Keras Functional API:
x = tf.keras.Input((28, 28, 1))
y = tf.keras.layers.AveragePooling1D(pool_size=2, strides=2)(x)
model = tf.keras.Model(x, y)
Description
Returns | |
---|---|
The output tensor, of rank 3. |
Raises | |
---|---|
ValueError
|
if eager execution is enabled. |