tf.raw_ops.QuantizedMatMulWithBiasAndRequantize

tf.raw_ops.QuantizedMatMulWithBiasAndRequantize(
    a, b, bias, min_a, max_a, min_b, max_b, min_freezed_output, max_freezed_output,
    Toutput=tf.dtypes.quint8, transpose_a=False, transpose_b=False,
    input_quant_mode='MIN_FIRST', name=None
)

Args:

  • a: A Tensor. Must be one of the following types: qint8, quint8, qint32, qint16, quint16.
  • b: A Tensor. Must be one of the following types: qint8, quint8, qint32, qint16, quint16.
  • bias: A Tensor. Must be one of the following types: float32, qint32.
  • min_a: A Tensor of type float32.
  • max_a: A Tensor of type float32.
  • min_b: A Tensor of type float32.
  • max_b: A Tensor of type float32.
  • min_freezed_output: A Tensor of type float32.
  • max_freezed_output: A Tensor of type float32.
  • Toutput: An optional tf.DType from: tf.qint8, tf.quint8, tf.qint32, tf.qint16, tf.quint16. Defaults to tf.quint8.
  • transpose_a: An optional bool. Defaults to False.
  • transpose_b: An optional bool. Defaults to False.
  • input_quant_mode: An optional string from: "MIN_FIRST", "SCALED". Defaults to "MIN_FIRST".
  • name: A name for the operation (optional).

Returns:

A tuple of Tensor objects (out, min_out, max_out).

  • out: A Tensor of type Toutput.
  • min_out: A Tensor of type float32.
  • max_out: A Tensor of type float32.