concrete.ml.quantization.quantizers

module concrete.ml.quantization.quantizers

Quantization utilities for a numpy array/tensor.

Global Variables

• STABILITY_CONST

---

function fill_from_kwargs

fill_from_kwargs(obj, klass, **kwargs)

Fill a parameter set structure from kwargs parameters.

Args:

• obj: an object of type klass, if None the object is created if any of the type's members appear in the kwargs

• klass: the type of object to fill

• kwargs: parameter names and values to fill into an instance of the klass type

Returns:

• obj: an object of type klass

• kwargs: remaining parameter names and values that were not filled into obj

Raises:

• TypeError: if the types of the parameters in kwargs could not be converted to the corresponding types of members of klass

---

class QuantizationOptions

Options for quantization.

Determines the number of bits for quantization and the method of quantization of the values. Signed quantization allows negative quantized values. Symmetric quantization assumes the float values are distributed symmetrically around x=0 and assigns signed values around 0 to the float values. QAT (quantization aware training) quantization assumes the values are already quantized, taking a discrete set of values, and assigns these values to integers, computing only the scale.

method __init__

__init__(
    n_bits,
    is_signed: bool = False,
    is_symmetric: bool = False,
    is_qat: bool = False
) → None

---

property quant_options

Get a copy of the quantization parameters.

Returns:

• UniformQuantizationParameters: a copy of the current quantization parameters

---

method copy_opts

copy_opts(opts)

Copy the options from a different structure.

Args:

• opts (QuantizationOptions): structure to copy parameters from.

---

class MinMaxQuantizationStats

Calibration set statistics.

This class stores the statistics for the calibration set or for a calibration data batch. Currently we only store min/max to determine the quantization range. The min/max are computed from the calibration set.

---

property quant_stats

Get a copy of the calibration set statistics.

Returns:

• MinMaxQuantizationStats: a copy of the current quantization stats

---

method compute_quantization_stats

compute_quantization_stats(values: ndarray) → None

Compute the calibration set quantization statistics.

Args:

• values (numpy.ndarray): Calibration set on which to compute statistics.

---

method copy_stats

copy_stats(stats) → None

Copy the statistics from a different structure.

Args:

• stats (MinMaxQuantizationStats): structure to copy statistics from.

---

class UniformQuantizationParameters

Quantization parameters for uniform quantization.

This class stores the parameters used for quantizing real values to discrete integer values. The parameters are computed from quantization options and quantization statistics.

---

property quant_params

Get a copy of the quantization parameters.

Returns:

• UniformQuantizationParameters: a copy of the current quantization parameters

---

method compute_quantization_parameters

compute_quantization_parameters(
    options: QuantizationOptions,
    stats: MinMaxQuantizationStats
) → None

Compute the quantization parameters.

Args:

• options (QuantizationOptions): quantization options set

• stats (MinMaxQuantizationStats): calibrated statistics for quantization

---

method copy_params

copy_params(params) → None

Copy the parameters from a different structure.

Args:

• params (UniformQuantizationParameters): parameter structure to copy

---

class UniformQuantizer

Uniform quantizer.

Contains all information necessary for uniform quantization and provides quantization/dequantization functionality on numpy arrays.

Args:

• options (QuantizationOptions): Quantization options set

• stats (Optional[MinMaxQuantizationStats]): Quantization batch statistics set

• params (Optional[UniformQuantizationParameters]): Quantization parameters set (scale, zero-point)

method __init__

__init__(
    options: QuantizationOptions = None,
    stats: Optional[MinMaxQuantizationStats] = None,
    params: Optional[UniformQuantizationParameters] = None,
    **kwargs
)

---

property quant_options

Get a copy of the quantization parameters.

Returns:

• UniformQuantizationParameters: a copy of the current quantization parameters

---

property quant_params

Get a copy of the quantization parameters.

Returns:

• UniformQuantizationParameters: a copy of the current quantization parameters

---

property quant_stats

Get a copy of the calibration set statistics.

Returns:

• MinMaxQuantizationStats: a copy of the current quantization stats

---

method compute_quantization_parameters

compute_quantization_parameters(
    options: QuantizationOptions,
    stats: MinMaxQuantizationStats
) → None

Compute the quantization parameters.

Args:

• options (QuantizationOptions): quantization options set

• stats (MinMaxQuantizationStats): calibrated statistics for quantization

---

method compute_quantization_stats

compute_quantization_stats(values: ndarray) → None

Compute the calibration set quantization statistics.

Args:

• values (numpy.ndarray): Calibration set on which to compute statistics.

---

method copy_opts

copy_opts(opts)

Copy the options from a different structure.

Args:

• opts (QuantizationOptions): structure to copy parameters from.

---

method copy_params

copy_params(params) → None

Copy the parameters from a different structure.

Args:

• params (UniformQuantizationParameters): parameter structure to copy

---

method copy_stats

copy_stats(stats) → None

Copy the statistics from a different structure.

Args:

• stats (MinMaxQuantizationStats): structure to copy statistics from.

---

method dequant

dequant(qvalues: ndarray) → ndarray

Dequantize values.

Args:

• qvalues (numpy.ndarray): integer values to dequantize

Returns:

• numpy.ndarray: Dequantized float values.

---

method quant

quant(values: ndarray) → ndarray

Quantize values.

Args:

• values (numpy.ndarray): float values to quantize

Returns:

• numpy.ndarray: Integer quantized values.

---

class QuantizedArray

Abstraction of quantized array.

Contains float values and their quantized integer counter-parts. Quantization is performed by the quantizer member object. Float and int values are kept in sync. Having both types of values is useful since quantized operators in Concrete ML graphs might need one or the other depending on how the operator works (in float or in int). Moreover, when the encrypted function needs to return a value, it must return integer values.

See https://arxiv.org/abs/1712.05877.

Args:

• values (numpy.ndarray): Values to be quantized.

• n_bits (int): The number of bits to use for quantization.

• value_is_float (bool, optional): Whether the passed values are real (float) values or not. If False, the values will be quantized according to the passed scale and zero_point. Defaults to True.

• options (QuantizationOptions): Quantization options set

• stats (Optional[MinMaxQuantizationStats]): Quantization batch statistics set

• params (Optional[UniformQuantizationParameters]): Quantization parameters set (scale, zero-point)

• kwargs: Any member of the options, stats, params sets as a key-value pair. The parameter sets need to be completely parametrized if their members appear in kwargs.

method __init__

__init__(
    n_bits,
    values: Optional[ndarray],
    value_is_float: bool = True,
    options: QuantizationOptions = None,
    stats: Optional[MinMaxQuantizationStats] = None,
    params: Optional[UniformQuantizationParameters] = None,
    **kwargs
)

---

method dequant

dequant() → ndarray

Dequantize self.qvalues.

Returns:

• numpy.ndarray: Dequantized values.

---

method quant

quant() → Union[ndarray, NoneType]

Quantize self.values.

Returns:

• numpy.ndarray: Quantized values.

---

method update_quantized_values

update_quantized_values(qvalues: ndarray) → ndarray

Update qvalues to get their corresponding values using the related quantized parameters.

Args:

• qvalues (numpy.ndarray): Values to replace self.qvalues

Returns:

• values (numpy.ndarray): Corresponding values

---

method update_values

update_values(values: ndarray) → ndarray

Update values to get their corresponding qvalues using the related quantized parameters.

Args:

• values (numpy.ndarray): Values to replace self.values

Returns:

• qvalues (numpy.ndarray): Corresponding qvalues