Global max pooling operation for temporal data.

  data_format = "channels_last",
  keepdims = FALSE,



What to compose the new Layer instance with. Typically a Sequential model or a Tensor (e.g., as returned by layer_input()). The return value depends on object. If object is:

  • missing or NULL, the Layer instance is returned.

  • a Sequential model, the model with an additional layer is returned.

  • a Tensor, the output tensor from layer_instance(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.

Input shape

3D tensor with shape: (batch_size, steps, features).

Output shape

2D tensor with shape: (batch_size, channels)