Global average pooling operation for temporal data.
layer_global_average_pooling_1d(
object,
data_format = "channels_last",
keepdims = FALSE,
...
)
What to call the new Layer
instance with. Typically a keras
Model
, another Layer
, or a tf.Tensor
/KerasTensor
. If object
is
missing, the Layer
instance is returned, otherwise, layer(object)
is
returned.
One of channels_last
(default) or channels_first
.
The ordering of the dimensions in the inputs.
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
.
standard layer arguments.
3D tensor with shape: (batch_size, steps, features)
.
2D tensor with shape: (batch_size, channels)
Other pooling layers:
layer_average_pooling_1d()
,
layer_average_pooling_2d()
,
layer_average_pooling_3d()
,
layer_global_average_pooling_2d()
,
layer_global_average_pooling_3d()
,
layer_global_max_pooling_1d()
,
layer_global_max_pooling_2d()
,
layer_global_max_pooling_3d()
,
layer_max_pooling_1d()
,
layer_max_pooling_2d()
,
layer_max_pooling_3d()