concrete.ml.quantization.quantized_ops.md
Last updated
Was this helpful?
Last updated
Was this helpful?
concrete.ml.quantization.quantized_ops
Quantized versions of the ONNX operators for post training quantization.
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
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
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
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
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
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
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
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
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
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
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
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
QuantizedGemm
Quantized Gemm op.
__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
q_impl
QuantizedMatMul
Quantized MatMul op.
__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
q_impl
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
can_fuse
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
q_impl
QuantizedTanh
Quantized Tanh op.
property int_input_names
Get the names of encrypted integer tensors that are used by this op.
Returns: