FakeQuantWithMinMaxArgs

tensorflow C++ API

tensorflow::ops::FakeQuantWithMinMaxArgs

Fake-quantize the 'inputs' tensor, type float to 'outputs' tensor of same type.

Summary

Attributes [min; max] define the clamping range for the 'inputs' data. Op divides this range into 255 steps (total of 256 values), then replaces each 'inputs' value with the closest of the quantized step values. 'num_bits' is the bitwidth of the quantization; between 2 and 8, inclusive.

Quantization is called fake since the output is still in floating point.

Arguments:

• scope: A Scope object

Returns:

• Output : The outputs tensor.

FakeQuantWithMinMaxArgs block

Source link :https://github.com/EXPNUNI/enuSpaceTensorflow/blob/master/enuSpaceTensorflow/tf_array_ops.cpp

Argument:

• Scope scope : A Scope object (A scope is generated automatically each page. A scope is not connected.)
• Input inputs: A Tensor of type float.
• Attr attrs : An optional attribute value
  • min : An optional float. Defaults to -6.
  • max : An optional float. Defaults to 6.
  • num_bits : An optional int. Defaults to 8.

Attrs use ex)

Output:

• output : Output object of FakeQuantWithMinMaxArgs class object.

Result:

• std::vector(Tensor) result_output : A Tensor of type float .

Using Method