tf.raw_ops.RequantizationRangePerChannel

Computes requantization range per channel.

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

Args:

  • input: A Tensor. Must be one of the following types: qint8, quint8, qint32, qint16, quint16. The original input tensor.
  • input_min: A Tensor of type float32. The minimum value of the input tensor
  • input_max: A Tensor of type float32. The maximum value of the input tensor.
  • clip_value_max: A float. The maximum value of the output that needs to be clipped. Example: set this to 6 for Relu6.
  • 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.