com.microsoft.nchwc - GlobalMaxPool#

GlobalMaxPool - 1 (com.microsoft.nchwc)#

Version

  • name: GlobalMaxPool (GitHub)

  • domain: com.microsoft.nchwc

  • since_version: 1

  • function:

  • support_level:

  • shape inference:

This version of the operator has been available since version 1 of domain com.microsoft.nchwc.

Summary

For internal use.

Inputs

  • X (heterogeneous) - T:

Outputs

  • Y (heterogeneous) - T:

Examples

default

node = onnx.helper.make_node(
    "GlobalMaxPool",
    inputs=["x"],
    outputs=["y"],
)
x = np.random.randn(1, 3, 5, 5).astype(np.float32)
y = np.max(x, axis=tuple(range(2, np.ndim(x))), keepdims=True)
expect(node, inputs=[x], outputs=[y], name="test_globalmaxpool")

_globalmaxpool_precomputed

node = onnx.helper.make_node(
    "GlobalMaxPool",
    inputs=["x"],
    outputs=["y"],
)
x = np.array(
    [
        [
            [
                [1, 2, 3],
                [4, 5, 6],
                [7, 8, 9],
            ]
        ]
    ]
).astype(np.float32)
y = np.array([[[[9]]]]).astype(np.float32)
expect(node, inputs=[x], outputs=[y], name="test_globalmaxpool_precomputed")