ai.onnx.ml - Binarizer#

Binarizer - 1 (ai.onnx.ml)#

Version#

  • name: Binarizer (GitHub)

  • domain: ai.onnx.ml

  • since_version: 1

  • function: False

  • support_level: SupportType.COMMON

  • shape inference: True

This version of the operator has been available since version 1 of domain ai.onnx.ml.

Summary#

Maps the values of the input tensor to either 0 or 1, element-wise, based on the outcome of a comparison against a threshold value.

Attributes#

  • threshold - FLOAT (default is '0.0'):

    Values greater than this are mapped to 1, others to 0.

Inputs#

  • X (heterogeneous) - T:

    Data to be binarized

Outputs#

  • Y (heterogeneous) - T:

    Binarized output data

Type Constraints#

  • T in ( tensor(double), tensor(float), tensor(int32), tensor(int64) ):

    The input must be a tensor of a numeric type. The output will be of the same tensor type.

Examples#

default#

import numpy as np
import onnx

threshold = 1.0
node = onnx.helper.make_node(
    "Binarizer",
    inputs=["X"],
    outputs=["Y"],
    threshold=threshold,
    domain="ai.onnx.ml",
)
x = np.random.randn(3, 4, 5).astype(np.float32)
y = compute_binarizer(x, threshold)[0]

expect(node, inputs=[x], outputs=[y], name="test_ai_onnx_ml_binarizer")