module onnxrt.ops_cpu.op_quantize_linear

Short summary

module mlprodict.onnxrt.ops_cpu.op_quantize_linear

Runtime operator.

source on GitHub

Classes

class	truncated documentation
_CommonQuantizeLinear
DynamicQuantizeLinear	DynamicQuantizeLinear ===================== A Function to fuse calculation for Scale, Zero Point and FP32->8Bit convertion …
QuantizeLinear	QuantizeLinear ============== The linear quantization operator. It consumes a high precision tensor, a scale, and a zero …

Properties

property	truncated documentation
args_default	Returns the list of arguments as well as the list of parameters with the default values (close to the signature). …
args_default	Returns the list of arguments as well as the list of parameters with the default values (close to the signature). …
args_default	Returns the list of arguments as well as the list of parameters with the default values (close to the signature). …
args_default_modified	Returns the list of modified parameters.
args_default_modified	Returns the list of modified parameters.
args_default_modified	Returns the list of modified parameters.
args_mandatory	Returns the list of optional arguments.
args_mandatory	Returns the list of optional arguments.
args_mandatory	Returns the list of optional arguments.
args_optional	Returns the list of optional arguments.
args_optional	Returns the list of optional arguments.
args_optional	Returns the list of optional arguments.
atts_value	Returns all parameters in a dictionary.
atts_value	Returns all parameters in a dictionary.
atts_value	Returns all parameters in a dictionary.

Methods

method	truncated documentation
__init__
__init__
__init__
_run
_run
common_run
common_run

Documentation

Runtime operator.

source on GitHub

class mlprodict.onnxrt.ops_cpu.op_quantize_linear.DynamicQuantizeLinear(onnx_node, desc=None, **options)

Bases: OpRun

---

A Function to fuse calculation for Scale, Zero Point and FP32->8Bit convertion of FP32 Input data. Outputs Scale, ZeroPoint and Quantized Input for a given FP32 Input. Scale is calculated as: ``

y_scale = (max(x) - min(x))/(qmax - qmin) * where qmax and qmin are max and min values for quantization range .i.e [0, 255] in case of uint8 * data range is adjusted to include 0.

`` Zero point is calculated as: `` intermediate_zero_point = qmin - min(x)/y_scale y_zero_point = cast(round(saturate(itermediate_zero_point))) * where qmax and qmin are max and min values for quantization range .i.e [0, 255] in case of uint8 * for saturation, it saturates to [0, 255] if it’s uint8, or [-127, 127] if it’s int8. Right now only uint8 is supported. * rounding to nearest ties to even. `` Data quantization formula is: `` y = saturate (round (x / y_scale) + y_zero_point) * for saturation, it saturates to [0, 255] if it’s uint8, or [-127, 127] if it’s int8. Right now only uint8 is supported. * rounding to nearest ties to even. ``

Inputs

• x (heterogeneous)T1: Input tensor

Outputs

• y (heterogeneous)T2: Quantized output tensor

• y_scale (heterogeneous)tensor(float): Output scale. It’s a scalar, which means a per-tensor/layer quantization.

• y_zero_point (heterogeneous)T2: Output zero point. It’s a scalar, which means a per-tensor/layer quantization.

Type Constraints

• T1 tensor(float): Constrain ‘x’ to float tensor.

• T2 tensor(uint8): Constrain ‘y_zero_point’ and ‘y’ to 8-bit unsigned integer tensor.

Version

Onnx name: DynamicQuantizeLinear

This version of the operator has been available since version 11.

Runtime implementation: DynamicQuantizeLinear

__init__(onnx_node, desc=None, **options)

_run(x, attributes=None, verbose=0, fLOG=None)

Should be overwritten.

source on GitHub

class mlprodict.onnxrt.ops_cpu.op_quantize_linear.QuantizeLinear(onnx_node, desc=None, **options)

Bases: _CommonQuantizeLinear

---

The linear quantization operator. It consumes a high precision tensor, a scale, and a zero point to compute the low precision / quantized tensor. The scale factor and zero point must have same shape, and can be either a scalar for per-tensor / per layer quantization, or a 1-D tensor for per-axis quantization. The quantization formula is y = saturate ((x / y_scale) + y_zero_point). For saturation, it saturates to [0, 255] if it’s uint8, or [-128, 127] if it’s int8. For (x / y_scale), it’s rounding to nearest ties to even. Refer to https://en.wikipedia.org/wiki/Rounding for details. ‘y_zero_point’ and ‘y’ must have same type.

Attributes

• axis: (Optional) The axis of the quantization dimension of the input tensor. Ignored for per-tensor quantization. Negative value means counting dimensions from the back. Accepted range is [-r, r-1] where r = rank(input). Default value is nameaxisi1typeINT (INT)

Inputs

Between 2 and 3 inputs.

• x (heterogeneous)T1: N-D full precision Input tensor to be quantized.

• y_scale (heterogeneous)tensor(float): Scale for doing quantization to get ‘y’. It can be a scalar, which means per-tensor/layer quantization, or a 1-D Tensor for per-axis quantization.

• y_zero_point (optional, heterogeneous)T2: Zero point for doing quantization to get ‘y’. Shape must match y_scale. Default is uint8 with zero point of 0 if it’s not specified.

Outputs

• y (heterogeneous)T2: N-D quantized output tensor. It has same shape as input ‘x’.

Type Constraints

• T1 tensor(float), tensor(int32): Constrain ‘x’ to float or int32 tensor.

• T2 tensor(int8), tensor(uint8): Constrain ‘y_zero_point’ and ‘y’ to 8-bit integer tensor.

Version

Onnx name: QuantizeLinear

This version of the operator has been available since version 13.

Runtime implementation: QuantizeLinear

__init__(onnx_node, desc=None, **options)

_run(*args, attributes=None, verbose=0, fLOG=None)

Should be overwritten.

source on GitHub

class mlprodict.onnxrt.ops_cpu.op_quantize_linear._CommonQuantizeLinear(onnx_node, desc=None, expected_attributes=None, **options)

Bases: OpRun

__init__(onnx_node, desc=None, expected_attributes=None, **options)