Website

concrete.ml.quantization.quantized_ops.md

module concrete.ml.quantization.quantized_ops

Quantized versions of the ONNX operators for post training quantization.

class QuantizedSigmoid

Quantized sigmoid op.

property int_input_names

Get the names of encrypted integer tensors that are used by this op.

Returns:

  • Set[str]: the names of the tensors

class QuantizedHardSigmoid

Quantized HardSigmoid op.

property int_input_names

Get the names of encrypted integer tensors that are used by this op.

Returns:

  • Set[str]: the names of the tensors

class QuantizedRelu

Quantized Relu op.

property int_input_names

Get the names of encrypted integer tensors that are used by this op.

Returns:

  • Set[str]: the names of the tensors

class QuantizedPRelu

Quantized PRelu op.

property int_input_names

Get the names of encrypted integer tensors that are used by this op.

Returns:

  • Set[str]: the names of the tensors

class QuantizedLeakyRelu

Quantized LeakyRelu op.

property int_input_names

Get the names of encrypted integer tensors that are used by this op.

Returns:

  • Set[str]: the names of the tensors

class QuantizedHardSwish

Quantized Hardswish op.

property int_input_names

Get the names of encrypted integer tensors that are used by this op.

Returns:

  • Set[str]: the names of the tensors

class QuantizedElu

Quantized Elu op.

property int_input_names

Get the names of encrypted integer tensors that are used by this op.

Returns:

  • Set[str]: the names of the tensors

class QuantizedSelu

Quantized Selu op.

property int_input_names

Get the names of encrypted integer tensors that are used by this op.

Returns:

  • Set[str]: the names of the tensors

class QuantizedCelu

Quantized Celu op.

property int_input_names

Get the names of encrypted integer tensors that are used by this op.

Returns:

  • Set[str]: the names of the tensors

class QuantizedClip

Quantized clip op.

property int_input_names

Get the names of encrypted integer tensors that are used by this op.

Returns:

  • Set[str]: the names of the tensors

class QuantizedRound

Quantized round op.

property int_input_names

Get the names of encrypted integer tensors that are used by this op.

Returns:

  • Set[str]: the names of the tensors

class QuantizedPow

Quantized pow op.

Only works for a float constant power. This operation will be fused to a (potentially larger) TLU.

property int_input_names

Get the names of encrypted integer tensors that are used by this op.

Returns:

  • Set[str]: the names of the tensors

class QuantizedGemm

Quantized Gemm op.

method __init__

__init__(
    n_bits_output: int,
    op_instance_name: str,
    int_input_names: Set[str] = None,
    constant_inputs: Optional[Dict[str, Any], Dict[int, Any]] = None,
    input_quant_opts: QuantizationOptions = None,
    **attrs
) → None

property int_input_names

Get the names of encrypted integer tensors that are used by this op.

Returns:

  • Set[str]: the names of the tensors

method q_impl

q_impl(
    *q_inputs: Optional[ndarray, QuantizedArray],
    calibrate_rounding: bool = False,
    **attrs
) → Union[ndarray, QuantizedArray, NoneType]

class QuantizedMatMul

Quantized MatMul op.

method __init__

__init__(
    n_bits_output: int,
    op_instance_name: str,
    int_input_names: Set[str] = None,
    constant_inputs: Optional[Dict[str, Any], Dict[int, Any]] = None,
    input_quant_opts: QuantizationOptions = None,
    **attrs
) → None

property int_input_names

Get the names of encrypted integer tensors that are used by this op.

Returns:

  • Set[str]: the names of the tensors

method q_impl

q_impl(
    *q_inputs: Optional[ndarray, QuantizedArray],
    calibrate_rounding: bool = False,
    **attrs
) → Union[ndarray, QuantizedArray, NoneType]

class QuantizedAdd

Quantized Addition operator.

Can add either two variables (both encrypted) or a variable and a constant

property int_input_names

Get the names of encrypted integer tensors that are used by this op.

Returns:

  • Set[str]: the names of the tensors

method can_fuse

can_fuse() → bool

Determine if this op can be fused.

Add operation can be computed in float and fused if it operates over inputs produced by a single integer tensor. For example the expression x + x * 1.75, where x is an encrypted tensor, can be computed with a single TLU.

Returns:

  • bool: Whether the number of integer input tensors allows computing this op as a TLU

method q_impl

q_impl(
    *q_inputs: Optional[ndarray, QuantizedArray],
    **attrs
) → Union[ndarray, QuantizedArray, NoneType]

class QuantizedTanh

Quantized Tanh op.

property int_input_names

Get the names of encrypted integer tensors that are used by this op.

Returns:

  • Set[str]: the names of the tensors

class QuantizedSoftplus

Quantized Softplus op.

property int_input_names

Get the names of encrypted integer tensors that are used by this op.

Returns:

  • Set[str]: the names of the tensors

class QuantizedExp

Quantized Exp op.

property int_input_names

Get the names of encrypted integer tensors that are used by this op.

Returns:

  • Set[str]: the names of the tensors

class QuantizedLog

Quantized Log op.

property int_input_names

Get the names of encrypted integer tensors that are used by this op.

Returns:

  • Set[str]: the names of the tensors

class QuantizedAbs

Quantized Abs op.

property int_input_names

Get the names of encrypted integer tensors that are used by this op.

Returns:

  • Set[str]: the names of the tensors

class QuantizedIdentity

Quantized Identity op.

property int_input_names

Get the names of encrypted integer tensors that are used by this op.

Returns:

  • Set[str]: the names of the tensors

method q_impl

q_impl(
    *q_inputs: Optional[ndarray, QuantizedArray],
    **attrs
) → Union[ndarray, QuantizedArray, NoneType]

class QuantizedReshape

Quantized Reshape op.

property int_input_names

Get the names of encrypted integer tensors that are used by this op.

Returns:

  • Set[str]: the names of the tensors

method can_fuse

can_fuse() → bool

Determine if this op can be fused.

Max Pooling operation can not be fused since it must be performed over integer tensors and it combines different elements of the input tensors.

Returns:

  • bool: False, this operation can not be fused as it adds different encrypted integers

method q_impl

q_impl(
    *q_inputs: Optional[ndarray, QuantizedArray],
    **attrs
) → Union[ndarray, QuantizedArray, NoneType]

Reshape the input integer encrypted tensor.

Args:

  • q_inputs: an encrypted integer tensor at index 0 and one constant shape at index 1

  • attrs: additional optional reshape options

Returns:

  • result (QuantizedArray): reshaped encrypted integer tensor

class QuantizedConv

Quantized Conv op.

method __init__

__init__(
    n_bits_output: int,
    op_instance_name: str,
    int_input_names: Set[str] = None,
    constant_inputs: Optional[Dict[str, Any], Dict[int, Any]] = None,
    input_quant_opts: QuantizationOptions = None,
    **attrs
) → None

Construct the quantized convolution operator and retrieve parameters.

Args:

  • n_bits_output: number of bits for the quantization of the outputs of this operator

  • op_instance_name (str): The name that should be assigned to this operation, used to retrieve it later or get debugging information about this op (bit-width, value range, integer intermediary values, op-specific error messages). Usually this name is the same as the ONNX operation name for which this operation is constructed.

  • int_input_names: names of integer tensors that are taken as input for this operation

  • constant_inputs: the weights and activations

  • input_quant_opts: options for the input quantizer

  • attrs: convolution options

  • dilations (Tuple[int]): dilation of the kernel. Default to 1 on all dimensions.

  • group (int): number of convolution groups. Default to 1.

  • kernel_shape (Tuple[int]): shape of the kernel. Should have 2 elements for 2d conv

  • pads (Tuple[int]): padding in ONNX format (begin, end) on each axis

  • strides (Tuple[int]): stride of the convolution on each axis

property int_input_names

Get the names of encrypted integer tensors that are used by this op.

Returns:

  • Set[str]: the names of the tensors

method q_impl

q_impl(
    *q_inputs: Optional[ndarray, QuantizedArray],
    calibrate_rounding: bool = False,
    **attrs
) → Union[ndarray, QuantizedArray, NoneType]

Compute the quantized convolution between two quantized tensors.

Allows an optional quantized bias.

Args:

  • q_inputs: input tuple, contains

  • x (numpy.ndarray): input data. Shape is N x C x H x W for 2d

  • w (numpy.ndarray): weights tensor. Shape is (O x I x Kh x Kw) for 2d

  • b (numpy.ndarray, Optional): bias tensor, Shape is (O,)

  • calibrate_rounding (bool): Whether to calibrate rounding

  • attrs: convolution options handled in constructor

Returns:

  • res (QuantizedArray): result of the quantized integer convolution

class QuantizedAvgPool

Quantized Average Pooling op.

method __init__

__init__(
    n_bits_output: int,
    op_instance_name: str,
    int_input_names: Set[str] = None,
    constant_inputs: Optional[Dict[str, Any], Dict[int, Any]] = None,
    input_quant_opts: QuantizationOptions = None,
    **attrs
) → None

property int_input_names

Get the names of encrypted integer tensors that are used by this op.

Returns:

  • Set[str]: the names of the tensors

method q_impl

q_impl(
    *q_inputs: Optional[ndarray, QuantizedArray],
    calibrate_rounding: bool = False,
    **attrs
) → Union[ndarray, QuantizedArray, NoneType]

class QuantizedMaxPool

Quantized Max Pooling op.

method __init__

__init__(
    n_bits_output: int,
    op_instance_name: str,
    int_input_names: Set[str] = None,
    constant_inputs: Optional[Dict[str, Any], Dict[int, Any]] = None,
    input_quant_opts: QuantizationOptions = None,
    **attrs
) → None

property int_input_names

Get the names of encrypted integer tensors that are used by this op.

Returns:

  • Set[str]: the names of the tensors

method can_fuse

can_fuse() → bool

Determine if this op can be fused.

Max Pooling operation can not be fused since it must be performed over integer tensors and it combines different elements of the input tensors.

Returns:

  • bool: False, this operation can not be fused as it adds different encrypted integers

method q_impl

q_impl(
    *q_inputs: Optional[ndarray, QuantizedArray],
    **attrs
) → Union[ndarray, QuantizedArray, NoneType]

class QuantizedPad

Quantized Padding op.

method __init__

__init__(
    n_bits_output: int,
    op_instance_name: str,
    int_input_names: Set[str] = None,
    constant_inputs: Optional[Dict[str, Any], Dict[int, Any]] = None,
    input_quant_opts: QuantizationOptions = None,
    **attrs
) → None

property int_input_names

Get the names of encrypted integer tensors that are used by this op.

Returns:

  • Set[str]: the names of the tensors

method can_fuse

can_fuse() → bool

Determine if this op can be fused.

Pad operation cannot be fused since it must be performed over integer tensors.

Returns:

  • bool: False, this operation cannot be fused as it is manipulates integer tensors

method q_impl

q_impl(
    *q_inputs: Optional[ndarray, QuantizedArray],
    calibrate_rounding: bool = False,
    **attrs
) → Union[ndarray, QuantizedArray, NoneType]

class QuantizedWhere

Where operator on quantized arrays.

Supports only constants for the results produced on the True/False branches.

method __init__

__init__(
    n_bits_output: int,
    op_instance_name: str,
    int_input_names: Set[str] = None,
    constant_inputs: Optional[Dict[str, Any], Dict[int, Any]] = None,
    input_quant_opts: QuantizationOptions = None,
    **attrs
) → None

property int_input_names

Get the names of encrypted integer tensors that are used by this op.

Returns:

  • Set[str]: the names of the tensors

class QuantizedCast

Cast the input to the required data type.

In FHE we only support a limited number of output types. Booleans are cast to integers.

property int_input_names

Get the names of encrypted integer tensors that are used by this op.

Returns:

  • Set[str]: the names of the tensors

class QuantizedGreater

Comparison operator >.

Only supports comparison with a constant.

method __init__

__init__(
    n_bits_output: int,
    op_instance_name: str,
    int_input_names: Set[str] = None,
    constant_inputs: Optional[Dict[str, Any], Dict[int, Any]] = None,
    input_quant_opts: QuantizationOptions = None,
    **attrs
) → None

property int_input_names

Get the names of encrypted integer tensors that are used by this op.

Returns:

  • Set[str]: the names of the tensors

class QuantizedGreaterOrEqual

Comparison operator >=.

Only supports comparison with a constant.

method __init__

__init__(
    n_bits_output: int,
    op_instance_name: str,
    int_input_names: Set[str] = None,
    constant_inputs: Optional[Dict[str, Any], Dict[int, Any]] = None,
    input_quant_opts: QuantizationOptions = None,
    **attrs
) → None

property int_input_names

Get the names of encrypted integer tensors that are used by this op.

Returns:

  • Set[str]: the names of the tensors

class QuantizedLess

Comparison operator <.

Only supports comparison with a constant.

method __init__

__init__(
    n_bits_output: int,
    op_instance_name: str,
    int_input_names: Set[str] = None,
    constant_inputs: Optional[Dict[str, Any], Dict[int, Any]] = None,
    input_quant_opts: QuantizationOptions = None,
    **attrs
) → None

property int_input_names

Get the names of encrypted integer tensors that are used by this op.

Returns:

  • Set[str]: the names of the tensors

class QuantizedLessOrEqual

Comparison operator <=.

Only supports comparison with a constant.

method __init__

__init__(
    n_bits_output: int,
    op_instance_name: str,
    int_input_names: Set[str] = None,
    constant_inputs: Optional[Dict[str, Any], Dict[int, Any]] = None,
    input_quant_opts: QuantizationOptions = None,
    **attrs
) → None

property int_input_names

Get the names of encrypted integer tensors that are used by this op.

Returns:

  • Set[str]: the names of the tensors

class QuantizedOr

Or operator ||.

This operation is not really working as a quantized operation. It just works when things got fused, as in e.g., Act(x) = x || (x + 42))

property int_input_names

Get the names of encrypted integer tensors that are used by this op.

Returns:

  • Set[str]: the names of the tensors

class QuantizedDiv

Div operator /.

This operation is not really working as a quantized operation. It just works when things got fused, as in e.g., Act(x) = 1000 / (x + 42))

property int_input_names

Get the names of encrypted integer tensors that are used by this op.

Returns:

  • Set[str]: the names of the tensors

class QuantizedMul

Multiplication operator.

Only multiplies an encrypted tensor with a float constant for now. This operation will be fused to a (potentially larger) TLU.

property int_input_names

Get the names of encrypted integer tensors that are used by this op.

Returns:

  • Set[str]: the names of the tensors

class QuantizedSub

Subtraction operator.

This works the same as addition on both encrypted - encrypted and on encrypted - constant.

property int_input_names

Get the names of encrypted integer tensors that are used by this op.

Returns:

  • Set[str]: the names of the tensors

method can_fuse

can_fuse() → bool

Determine if this op can be fused.

Add operation can be computed in float and fused if it operates over inputs produced by a single integer tensor. For example the expression x + x * 1.75, where x is an encrypted tensor, can be computed with a single TLU.

Returns:

  • bool: Whether the number of integer input tensors allows computing this op as a TLU

method q_impl

q_impl(
    *q_inputs: Optional[ndarray, QuantizedArray],
    **attrs
) → Union[ndarray, QuantizedArray, NoneType]

class QuantizedBatchNormalization

Quantized Batch normalization with encrypted input and in-the-clear normalization params.

property int_input_names

Get the names of encrypted integer tensors that are used by this op.

Returns:

  • Set[str]: the names of the tensors

class QuantizedFlatten

Quantized flatten for encrypted inputs.

property int_input_names

Get the names of encrypted integer tensors that are used by this op.

Returns:

  • Set[str]: the names of the tensors

method can_fuse

can_fuse() → bool

Determine if this op can be fused.

Flatten operation cannot be fused since it must be performed over integer tensors.

Returns:

  • bool: False, this operation cannot be fused as it is manipulates integer tensors.

method q_impl

q_impl(
    *q_inputs: Optional[ndarray, QuantizedArray],
    **attrs
) → Union[ndarray, QuantizedArray, NoneType]

Flatten the input integer encrypted tensor.

Args:

  • q_inputs: an encrypted integer tensor at index 0

  • attrs: contains axis attribute

Returns:

  • result (QuantizedArray): reshaped encrypted integer tensor

class QuantizedReduceSum

ReduceSum with encrypted input.

method __init__

__init__(
    n_bits_output: int,
    op_instance_name: str,
    int_input_names: Set[str] = None,
    constant_inputs: Optional[Dict[str, Any], Dict[int, Any]] = None,
    input_quant_opts: Optional[QuantizationOptions] = None,
    **attrs
) → None

Construct the quantized ReduceSum operator and retrieve parameters.

Args:

  • n_bits_output (int): Number of bits for the operator's quantization of outputs.

  • op_instance_name (str): The name that should be assigned to this operation, used to retrieve it later or get debugging information about this op (bit-width, value range, integer intermediary values, op-specific error messages). Usually this name is the same as the ONNX operation name for which this operation is constructed.

  • int_input_names (Optional[Set[str]]): Names of input integer tensors. Default to None.

  • constant_inputs (Optional[Dict]): Input constant tensor.

  • axes (Optional[numpy.ndarray]): Array of integers along which to reduce. The default is to reduce over all the dimensions of the input tensor if 'noop_with_empty_axes' is false, else act as an Identity op when 'noop_with_empty_axes' is true. Accepted range is [-r, r-1] where r = rank(data). Default to None.

  • input_quant_opts (Optional[QuantizationOptions]): Options for the input quantizer. Default to None.

  • attrs (dict): RecuseSum options.

  • keepdims (int): Keep the reduced dimension or not, 1 means keeping the input dimension, 0 will reduce it along the given axis. Default to 1.

  • noop_with_empty_axes (int): Defines behavior if 'axes' is empty or set to None. Default behavior with 0 is to reduce all axes. When axes is empty and this attribute is set to true 1, input tensor will not be reduced, and the output tensor would be equivalent to input tensor. Default to 0.

property int_input_names

Get the names of encrypted integer tensors that are used by this op.

Returns:

  • Set[str]: the names of the tensors

method calibrate

calibrate(*inputs: ndarray) → ndarray

Create corresponding QuantizedArray for the output of the activation function.

Args:

  • *inputs (numpy.ndarray): Calibration sample inputs.

Returns:

  • numpy.ndarray: The output values for the provided calibration samples.

method q_impl

q_impl(
    *q_inputs: Optional[ndarray, QuantizedArray],
    **attrs
) → Union[ndarray, QuantizedArray, NoneType]

Sum the encrypted tensor's values along the given axes.

Args:

  • q_inputs (QuantizedArray): An encrypted integer tensor at index 0.

  • attrs (Dict): Options are handled in constructor.

Returns:

  • (QuantizedArray): The sum of all values along the given axes.

class QuantizedErf

Quantized erf op.

property int_input_names

Get the names of encrypted integer tensors that are used by this op.

Returns:

  • Set[str]: the names of the tensors

class QuantizedNot

Quantized Not op.

property int_input_names

Get the names of encrypted integer tensors that are used by this op.

Returns:

  • Set[str]: the names of the tensors

class QuantizedBrevitasQuant

Brevitas uniform quantization with encrypted input.

method __init__

__init__(
    n_bits_output: int,
    op_instance_name: str,
    int_input_names: Set[str] = None,
    constant_inputs: Optional[Dict[str, Any], Dict[int, Any]] = None,
    input_quant_opts: Optional[QuantizationOptions] = None,
    **attrs
) → None

Construct the Brevitas quantization operator.

Args:

  • n_bits_output (int): Number of bits for the operator's quantization of outputs. Not used, will be overridden by the bit_width in ONNX

  • op_instance_name (str): The name that should be assigned to this operation, used to retrieve it later or get debugging information about this op (bit-width, value range, integer intermediary values, op-specific error messages). Usually this name is the same as the ONNX operation name for which this operation is constructed.

  • int_input_names (Optional[Set[str]]): Names of input integer tensors. Default to None.

  • constant_inputs (Optional[Dict]): Input constant tensor.

  • scale (float): Quantizer scale

  • zero_point (float): Quantizer zero-point

  • bit_width (int): Number of bits of the integer representation

  • input_quant_opts (Optional[QuantizationOptions]): Options for the input quantizer. Default to None. attrs (dict):

  • rounding_mode (str): Rounding mode (default and only accepted option is "ROUND")

  • signed (int): Whether this op quantizes to signed integers (default 1),

  • narrow (int): Whether this op quantizes to a narrow range of integers e.g., [-2n_bits-1 .. 2n_bits-1] (default 0),

property int_input_names

Get the names of encrypted integer tensors that are used by this op.

Returns:

  • Set[str]: the names of the tensors

method calibrate

calibrate(*inputs: ndarray) → ndarray

Create corresponding QuantizedArray for the output of Quantization function.

Args:

  • *inputs (numpy.ndarray): Calibration sample inputs.

Returns:

  • numpy.ndarray: the output values for the provided calibration samples.

method q_impl

q_impl(
    *q_inputs: Optional[ndarray, QuantizedArray],
    **attrs
) → Union[ndarray, QuantizedArray, NoneType]

Quantize values.

Args:

  • q_inputs: an encrypted integer tensor at index 0, scale, zero_point, n_bits at indices 1,2,3

  • attrs: additional optional attributes

Returns:

  • result (QuantizedArray): reshaped encrypted integer tensor

class QuantizedTranspose

Transpose operator for quantized inputs.

This operator performs quantization and transposes the encrypted data. When the inputs are pre-computed QAT the input is only quantized if needed.

property int_input_names

Get the names of encrypted integer tensors that are used by this op.

Returns:

  • Set[str]: the names of the tensors

method can_fuse

can_fuse() → bool

Determine if this op can be fused.

Transpose can not be fused since it must be performed over integer tensors as it moves around different elements of these input tensors.

Returns:

  • bool: False, this operation can not be fused as it copies encrypted integers

method q_impl

q_impl(
    *q_inputs: Optional[ndarray, QuantizedArray],
    **attrs
) → Union[ndarray, QuantizedArray, NoneType]

Transpose the input integer encrypted tensor.

Args:

  • q_inputs: an encrypted integer tensor at index 0 and one constant shape at index 1

  • attrs: additional optional reshape options

Returns:

  • result (QuantizedArray): transposed encrypted integer tensor

class QuantizedFloor

Quantized Floor op.

property int_input_names

Get the names of encrypted integer tensors that are used by this op.

Returns:

  • Set[str]: the names of the tensors

class QuantizedMax

Quantized Max op.

property int_input_names

Get the names of encrypted integer tensors that are used by this op.

Returns:

  • Set[str]: the names of the tensors

class QuantizedMin

Quantized Min op.

property int_input_names

Get the names of encrypted integer tensors that are used by this op.

Returns:

  • Set[str]: the names of the tensors

class QuantizedNeg

Quantized Neg op.

property int_input_names

Get the names of encrypted integer tensors that are used by this op.

Returns:

  • Set[str]: the names of the tensors

class QuantizedSign

Quantized Neg op.

property int_input_names

Get the names of encrypted integer tensors that are used by this op.

Returns:

  • Set[str]: the names of the tensors

class QuantizedUnsqueeze

Unsqueeze operator.

property int_input_names

Get the names of encrypted integer tensors that are used by this op.

Returns:

  • Set[str]: the names of the tensors

method can_fuse

can_fuse() → bool

Determine if this op can be fused.

Unsqueeze can not be fused since it must be performed over integer tensors as it reshapes an encrypted tensor.

Returns:

  • bool: False, this operation can not be fused as it operates on encrypted tensors

method q_impl

q_impl(
    *q_inputs: Optional[ndarray, QuantizedArray],
    **attrs
) → Union[ndarray, QuantizedArray, NoneType]

Unsqueeze the input tensors on a given axis.

Args:

  • q_inputs: an encrypted integer tensor at index 0, axes at index 1

  • attrs: additional optional unsqueeze options

Returns:

  • result (QuantizedArray): unsqueezed encrypted integer tensor

class QuantizedConcat

Concatenate operator.

property int_input_names

Get the names of encrypted integer tensors that are used by this op.

Returns:

  • Set[str]: the names of the tensors

method can_fuse

can_fuse() → bool

Determine if this op can be fused.

Concatenation can not be fused since it must be performed over integer tensors as it copies encrypted integers from one tensor to another.

Returns:

  • bool: False, this operation can not be fused as it copies encrypted integers

method q_impl

q_impl(
    *q_inputs: Optional[ndarray, QuantizedArray],
    **attrs
) → Union[ndarray, QuantizedArray, NoneType]

Concatenate the input tensors on a given axis.

Args:

  • q_inputs: an encrypted integer tensor

  • attrs: additional optional concatenate options

Returns:

  • result (QuantizedArray): concatenated encrypted integer tensor

class QuantizedSqueeze

Squeeze operator.

property int_input_names

Get the names of encrypted integer tensors that are used by this op.

Returns:

  • Set[str]: the names of the tensors

method can_fuse

can_fuse() → bool

Determine if this op can be fused.

Squeeze can not be fused since it must be performed over integer tensors as it reshapes encrypted tensors.

Returns:

  • bool: False, this operation can not be fused as it reshapes encrypted tensors

method q_impl

q_impl(
    *q_inputs: Optional[ndarray, QuantizedArray],
    **attrs
) → Union[ndarray, QuantizedArray, NoneType]

Squeeze the input tensors on a given axis.

Args:

  • q_inputs: an encrypted integer tensor at index 0, axes at index 1

  • attrs: additional optional squeeze options

Returns:

  • result (QuantizedArray): squeezed encrypted integer tensor

class ONNXShape

Shape operator.

property int_input_names

Get the names of encrypted integer tensors that are used by this op.

Returns:

  • Set[str]: the names of the tensors

method can_fuse

can_fuse() → bool

Determine if this op can be fused.

This operation returns the shape of the tensor and thus can not be fused into a univariate TLU.

Returns:

  • bool: False, this operation can not be fused

method q_impl

q_impl(
    *q_inputs: Optional[ndarray, QuantizedArray],
    **attrs
) → Union[ndarray, QuantizedArray, NoneType]

class ONNXConstantOfShape

ConstantOfShape operator.

property int_input_names

Get the names of encrypted integer tensors that are used by this op.

Returns:

  • Set[str]: the names of the tensors

method can_fuse

can_fuse() → bool

Determine if this op can be fused.

This operation returns a new encrypted tensor and thus can not be fused.

Returns:

  • bool: False, this operation can not be fused

class ONNXGather

Gather operator.

Returns values at requested indices from the input tensor.

property int_input_names

Get the names of encrypted integer tensors that are used by this op.

Returns:

  • Set[str]: the names of the tensors

method can_fuse

can_fuse() → bool

Determine if this op can be fused.

This operation returns values from a tensor and thus can not be fused into a univariate TLU.

Returns:

  • bool: False, this operation can not be fused

method q_impl

q_impl(
    *q_inputs: Optional[ndarray, QuantizedArray],
    **attrs
) → Union[ndarray, QuantizedArray, NoneType]

class ONNXSlice

Slice operator.

property int_input_names

Get the names of encrypted integer tensors that are used by this op.

Returns:

  • Set[str]: the names of the tensors

method can_fuse

can_fuse() → bool

Determine if this op can be fused.

This operation returns values from a tensor and thus can not be fused into a univariate TLU.

Returns:

  • bool: False, this operation can not be fused

method q_impl

q_impl(
    *q_inputs: Optional[ndarray, QuantizedArray],
    **attrs
) → Union[ndarray, QuantizedArray, NoneType]
Previousconcrete.ml.quantization.quantized_module.mdNextconcrete.ml.quantization.quantizers.md

Last updated

Was this helpful?