► Keras 2 API documentation / Layers API / Pooling layers / GlobalMaxPooling2D layer

GlobalMaxPooling2D layer

[source]

GlobalMaxPooling2D class

tf_keras.layers.GlobalMaxPooling2D(data_format=None, keepdims=False, **kwargs)

Global max pooling operation for spatial data.

Examples

>>> input_shape = (2, 4, 5, 3)
>>> x = tf.random.normal(input_shape)
>>> y = tf.keras.layers.GlobalMaxPooling2D()(x)
>>> print(y.shape)
(2, 3)

Arguments

  • 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 TF-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_max or np.max.

Input shape

  • 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).

Output shape

  • 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)
GlobalMaxPooling2D layer
GlobalMaxPooling2D class