com.microsoft - DequantizeLinear#

DequantizeLinear - 1#

Version

  • name: DequantizeLinear (GitHub)

  • domain: com.microsoft

  • since_version: 1

  • function:

  • support_level: SupportType.COMMON

  • shape inference: True

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

Summary

Attributes

  • axis - INT : The axis along which same quantization parameters are applied. It’s optional.If it’s not specified, it means per-tensor quantization and input ‘x_scale’ and ‘x_zero_point’ must be scalars.If it’s specified, it means per ‘axis’ quantization and input ‘x_scale’ and ‘x_zero_point’ must be 1-D tensors.

Inputs

  • x (heterogeneous) - T1:

  • x_scale (heterogeneous) - T2:

  • x_zero_point (heterogeneous) - T1:

Outputs

  • y (heterogeneous) - T2:

Type Constraints

  • T1 in ( tensor(int8), tensor(uint8) ): Constrain ‘x’ and ‘x_zero_point’ to 8-bit integer tensors.

  • T2 in ( tensor(float), tensor(float16) ): Constrain ‘y’, ‘x_scale’ to float tensors.

Examples

default

import numpy as np
import onnx

node = onnx.helper.make_node(
    "DequantizeLinear",
    inputs=["x", "x_scale", "x_zero_point"],
    outputs=["y"],
)

# scalar zero point and scale
x = np.array([0, 3, 128, 255]).astype(np.uint8)
x_scale = np.float32(2)
x_zero_point = np.uint8(128)
y = np.array([-256, -250, 0, 254], dtype=np.float32)

expect(
    node,
    inputs=[x, x_scale, x_zero_point],
    outputs=[y],
    name="test_dequantizelinear",
)

_axis

import numpy as np
import onnx

node = onnx.helper.make_node(
    "DequantizeLinear",
    inputs=["x", "x_scale", "x_zero_point"],
    outputs=["y"],
)

# 1-D tensor zero point and scale of size equal to axis 1 of the input tensor
x = np.array(
    [
        [
            [[3, 89], [34, 200], [74, 59]],
            [[5, 24], [24, 87], [32, 13]],
            [[245, 99], [4, 142], [121, 102]],
        ],
    ],
    dtype=np.uint8,
)
x_scale = np.array([2, 4, 5], dtype=np.float32)
x_zero_point = np.array([84, 24, 196], dtype=np.uint8)
y = (
    x.astype(np.float32) - x_zero_point.reshape(1, 3, 1, 1).astype(np.float32)
) * x_scale.reshape(1, 3, 1, 1)

expect(
    node,
    inputs=[x, x_scale, x_zero_point],
    outputs=[y],
    name="test_dequantizelinear_axis",
)

_e4m3fn

import numpy as np
import onnx

node = onnx.helper.make_node(
    "DequantizeLinear",
    inputs=["x", "x_scale"],
    outputs=["y"],
)

# scalar zero point and scale
x = make_tensor("x", TensorProto.FLOAT8E4M3FN, [5], [0, 0.5, 1, 448, 104])
x_scale = np.float32(2)
y = np.array([0.0, 1.0, 2.0, 896.0, 208.0], dtype=np.float32)

expect(
    node,
    inputs=[x, x_scale],
    outputs=[y],
    name="test_dequantizelinear_e4m3fn",
)

_e5m2

import numpy as np
import onnx

node = onnx.helper.make_node(
    "DequantizeLinear",
    inputs=["x", "x_scale"],
    outputs=["y"],
)

# scalar zero point and scale
x = make_tensor("x", TensorProto.FLOAT8E5M2, [5], [0, 0.5, 1, 49152, 96])
x_scale = np.float32(2)
y = np.array([0.0, 1.0, 2.0, 98304.0, 192.0], dtype=np.float32)

expect(
    node,
    inputs=[x, x_scale],
    outputs=[y],
    name="test_dequantizelinear_e5m2",
)