tf.raw_ops.RequantizationRange

Computes a range that covers the actual values present in a quantized tensor.

tf.raw_ops.RequantizationRange(
    input, input_min, input_max, name=None
)

Given a quantized tensor described by (input, input_min, input_max), outputs a range that covers the actual values present in that tensor. This op is typically used to produce the requested_output_min and requested_output_max for Requantize.

Args:

  • input: A Tensor. Must be one of the following types: qint8, quint8, qint32, qint16, quint16.
  • input_min: A Tensor of type float32. The float value that the minimum quantized input value represents.
  • input_max: A Tensor of type float32. The float value that the maximum quantized input value represents.
  • name: A name for the operation (optional).

Returns:

A tuple of Tensor objects (output_min, output_max).

  • output_min: A Tensor of type float32.
  • output_max: A Tensor of type float32.