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
)

aA Tensor. Must be one of the following types: qint8, quint8, qint32, qint16, quint16.
bA Tensor. Must be one of the following types: qint8, quint8, qint32, qint16, quint16.
biasA Tensor. Must be one of the following types: float32, qint32.
min_aA Tensor of type float32.
max_aA Tensor of type float32.
min_bA Tensor of type float32.
max_bA Tensor of type float32.
min_freezed_outputA Tensor of type float32.
max_freezed_outputA Tensor of type float32.
ToutputAn optional tf.DType from: tf.qint8, tf.quint8, tf.qint32, tf.qint16, tf.quint16. Defaults to tf.quint8.
transpose_aAn optional bool. Defaults to False.
transpose_bAn optional bool. Defaults to False.
input_quant_modeAn optional string from: "MIN_FIRST", "SCALED". Defaults to "MIN_FIRST".
nameA name for the operation (optional).

A tuple of Tensor objects (out, min_out, max_out).
outA Tensor of type Toutput.
min_outA Tensor of type float32.
max_outA Tensor of type float32.