max

Graph.max(x, axis=None, keepdims=False, *, name=None)

Find the maximum value in a tensor along one or multiple of its axes.

Parameters

  • x (np.ndarray or Tensor) – The tensor of which you want to find the maximum value.
  • axis (int or list [ int ] or None , optional) – The dimension or dimensions along which you want to search the tensor. Defaults to None, in which case this node returns the maximum value along all axes of the tensor.
  • keepdims (bool , optional) – Whether or not to retain summed axes in the output tensor. If True, each dimension in axis has size 1 in the result; otherwise, the dimensions in axis are removed from the result. Defaults to False.
  • name (str or None , optional) – The name of the node.

Returns

The maximum tensor obtained by searching the input tensor along the specified axes.

Return type

Tensor

SEE ALSO

Graph.min : Find the minimum value in a tensor along one or multiple of its axes.

Was this useful?