concrete.ml.quantization.base_quantized_op.md
Last updated
Last updated
concrete.ml.quantization.base_quantized_opBase Quantized Op class that implements quantization for a float numpy op.
ONNX_OPS_TO_NUMPY_IMPL
ALL_QUANTIZED_OPS
ONNX_OPS_TO_QUANTIZED_IMPL
DEFAULT_MODEL_BITS
QuantizedOpBase class for quantized ONNX ops implemented in numpy.
Args:
n_bits_output (int): The number of bits to use for the quantization of the output
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 (Set[str]): The set of names of integer tensors that are inputs to this op
constant_inputs (Optional[Union[Dict[str, Any], Dict[int, Any]]]): The constant tensors that are inputs to this op
input_quant_opts (QuantizationOptions): Input quantizer options, determine the quantization that is applied to input tensors (that are not constants)
__init__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
calibrateCreate 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.
call_implCall self.impl to centralize mypy bug workaround.
Args:
*inputs (numpy.ndarray): real valued inputs.
**attrs: the QuantizedOp attributes.
Returns:
numpy.ndarray: return value of self.impl
can_fuseDetermine if the operator impedes graph fusion.
This function shall be overloaded by inheriting classes to test self._int_input_names, to determine whether the operation can be fused to a TLU or not. For example an operation that takes inputs produced by a unique integer tensor can be fused to a TLU. Example: f(x) = x * (x + 1) can be fused. A function that does f(x) = x * (x @ w + 1) can't be fused.
Returns:
bool: whether this QuantizedOp instance produces Concrete code that can be fused to TLUs
dumpDump itself to a file.
Args:
file (TextIO): The file to dump the serialized object into.
dump_dictDump itself to a dict.
Returns:
metadata (Dict): Dict of serialized objects.
dumpsDump itself to a string.
Returns:
metadata (str): String of the serialized object.
load_dictLoad itself from a string.
Args:
metadata (Dict): Dict of serialized objects.
Returns:
QuantizedOp: The loaded object.
must_quantize_inputDetermine if an input must be quantized.
Quantized ops and numpy onnx ops take inputs and attributes. Inputs can be either constant or variable (encrypted). Note that this does not handle attributes, which are handled by QuantizedOp classes separately in their constructor.
Args:
input_name_or_idx (int): Index of the input to check.
Returns:
result (bool): Whether the input must be quantized (must be a QuantizedArray) or if it stays as a raw numpy.array read from ONNX.
op_typeGet the type of this operation.
Returns:
op_type (str): The type of this operation, in the ONNX referential
prepare_outputQuantize the output of the activation function.
The calibrate method needs to be called with sample data before using this function.
Args:
qoutput_activation (numpy.ndarray): Output of the activation function.
Returns:
QuantizedArray: Quantized output.
q_implExecute the quantized forward.
Args:
*q_inputs (ONNXOpInputOutputType): Quantized inputs.
**attrs: the QuantizedOp attributes.
Returns:
ONNXOpInputOutputType: The returned quantized value.
QuantizedOpUnivariateOfEncryptedAn univariate operator of an encrypted value.
This operation is not really operating as a quantized operation. It is useful when the computations get fused into a TLU, as in e.g., Act(x) = x || (x + 42)).
__init__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
calibrateCreate 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.
call_implCall self.impl to centralize mypy bug workaround.
Args:
*inputs (numpy.ndarray): real valued inputs.
**attrs: the QuantizedOp attributes.
Returns:
numpy.ndarray: return value of self.impl
can_fuseDetermine if this op can be fused.
This operation can be fused and computed in float when a single integer tensor generates both the operands. For example in the formula: f(x) = x || (x + 1) where x is an integer tensor.
Returns:
bool: Can fuse
dumpDump itself to a file.
Args:
file (TextIO): The file to dump the serialized object into.
dump_dictDump itself to a dict.
Returns:
metadata (Dict): Dict of serialized objects.
dumpsDump itself to a string.
Returns:
metadata (str): String of the serialized object.
load_dictLoad itself from a string.
Args:
metadata (Dict): Dict of serialized objects.
Returns:
QuantizedOp: The loaded object.
must_quantize_inputDetermine if an input must be quantized.
Quantized ops and numpy onnx ops take inputs and attributes. Inputs can be either constant or variable (encrypted). Note that this does not handle attributes, which are handled by QuantizedOp classes separately in their constructor.
Args:
input_name_or_idx (int): Index of the input to check.
Returns:
result (bool): Whether the input must be quantized (must be a QuantizedArray) or if it stays as a raw numpy.array read from ONNX.
op_typeGet the type of this operation.
Returns:
op_type (str): The type of this operation, in the ONNX referential
prepare_outputQuantize the output of the activation function.
The calibrate method needs to be called with sample data before using this function.
Args:
qoutput_activation (numpy.ndarray): Output of the activation function.
Returns:
QuantizedArray: Quantized output.
q_implExecute the quantized forward.
Args:
*q_inputs (ONNXOpInputOutputType): Quantized inputs.
**attrs: the QuantizedOp attributes.
Returns:
ONNXOpInputOutputType: The returned quantized value.
QuantizedMixingOpAn operator that mixes (adds or multiplies) together encrypted inputs.
Mixing operators cannot be fused to TLUs.
__init__Initialize quantized ops parameters plus specific parameters.
Args:
rounding_threshold_bits (Optional[int]): Number of bits to round to.
*args: positional argument to pass to the parent class.
**kwargs: named argument to pass to the parent class.
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
calibrateCreate 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.
call_implCall self.impl to centralize mypy bug workaround.
Args:
*inputs (numpy.ndarray): real valued inputs.
**attrs: the QuantizedOp attributes.
Returns:
numpy.ndarray: return value of self.impl
can_fuseDetermine if this op can be fused.
Mixing operations cannot be fused since it must be performed over integer tensors and it combines different encrypted elements of the input tensors. Mixing operations are Conv, MatMul, etc.
Returns:
bool: False, this operation cannot be fused as it adds different encrypted integers
cnp_roundRound the input array to the specified number of bits.
Args:
x (Union[numpy.ndarray, fhe.tracing.Tracer]): The input array to be rounded.
calibrate_rounding (bool): Whether to calibrate the rounding (compute the lsbs_to_remove)
Returns:
numpy.ndarray: The rounded array.
dumpDump itself to a file.
Args:
file (TextIO): The file to dump the serialized object into.
dump_dictDump itself to a dict.
Returns:
metadata (Dict): Dict of serialized objects.
dumpsDump itself to a string.
Returns:
metadata (str): String of the serialized object.
load_dictLoad itself from a string.
Args:
metadata (Dict): Dict of serialized objects.
Returns:
QuantizedOp: The loaded object.
make_output_quant_parametersBuild a quantized array from quantized integer results of the op and quantization params.
Args:
q_values (Union[numpy.ndarray, Any]): the quantized integer values to wrap in the QuantizedArray
scale (float): the pre-computed scale of the quantized values
zero_point (Union[int, float, numpy.ndarray]): the pre-computed zero_point of the q_values
Returns:
QuantizedArray: the quantized array that will be passed to the QuantizedModule output.
must_quantize_inputDetermine if an input must be quantized.
Quantized ops and numpy onnx ops take inputs and attributes. Inputs can be either constant or variable (encrypted). Note that this does not handle attributes, which are handled by QuantizedOp classes separately in their constructor.
Args:
input_name_or_idx (int): Index of the input to check.
Returns:
result (bool): Whether the input must be quantized (must be a QuantizedArray) or if it stays as a raw numpy.array read from ONNX.
op_typeGet the type of this operation.
Returns:
op_type (str): The type of this operation, in the ONNX referential
prepare_outputQuantize the output of the activation function.
The calibrate method needs to be called with sample data before using this function.
Args:
qoutput_activation (numpy.ndarray): Output of the activation function.
Returns:
QuantizedArray: Quantized output.
q_implExecute the quantized forward.
Args:
*q_inputs (ONNXOpInputOutputType): Quantized inputs.
**attrs: the QuantizedOp attributes.
Returns:
ONNXOpInputOutputType: The returned quantized value.