tf.keras.layers.GlobalAveragePooling2D

Global average pooling operation for spatial data.

Inherits From: Layer, Module

Main aliases

tf.keras.layers.GlobalAvgPool2D

 
tf.keras.layers.GlobalAveragePooling2D(
    data_format=None, keepdims=False, **kwargs
)

Examples:

input_shape = (2, 4, 5, 3)
x = tf.random.normal(input_shape)
y = tf.keras.layers.GlobalAveragePooling2D()(x)
print(y.shape)
(2, 3)

data_format A string, one of channels_last (default) or channels_first. The ordering of the dimensions in the inputs. channels_last corresponds to inputs with shape (batch, height, width, channels) while channels_first corresponds to inputs with shape (batch, channels, height, width). When unspecified, uses image_data_format value found in your Keras config file at ~/.keras/keras.json (if exists) else 'channels_last'. Defaults to 'channels_last'.
keepdims A boolean, whether to keep the spatial dimensions or not. If keepdims is False (default), the rank of the tensor is reduced for spatial dimensions. If keepdims is True, the spatial dimensions are retained with length 1. The behavior is the same as for tf.reduce_mean or np.mean.

  • If data_format='channels_last': 4D tensor with shape (batch_size, rows, cols, channels).
  • If data_format='channels_first': 4D tensor with shape (batch_size, channels, rows, cols).

  • If keepdims=False: 2D tensor with shape (batch_size, channels).
  • If keepdims=True:
    • If data_format='channels_last': 4D tensor with shape (batch_size, 1, 1, channels)
    • If data_format='channels_first': 4D tensor with shape (batch_size, channels, 1, 1)