tf.raw_ops.QuantizedInstanceNorm

Quantized Instance normalization.

tf.raw_ops.QuantizedInstanceNorm(
    x,
    x_min,
    x_max,
    output_range_given=False,
    given_y_min=0,
    given_y_max=0,
    variance_epsilon=1e-05,
    min_separation=0.001,
    name=None
)

xA Tensor. Must be one of the following types: qint8, quint8, qint32, qint16, quint16. A 4D input Tensor.
x_minA Tensor of type float32. The value represented by the lowest quantized input.
x_maxA Tensor of type float32. The value represented by the highest quantized input.
output_range_givenAn optional bool. Defaults to False. If True, given_y_min and given_y_min and given_y_max are used as the output range. Otherwise, the implementation computes the output range.
given_y_minAn optional float. Defaults to 0. Output in y_min if output_range_given is True.
given_y_maxAn optional float. Defaults to 0. Output in y_max if output_range_given is True.
variance_epsilonAn optional float. Defaults to 1e-05. A small float number to avoid dividing by 0.
min_separationAn optional float. Defaults to 0.001. Minimum value of y_max - y_min
nameA name for the operation (optional).

A tuple of Tensor objects (y, y_min, y_max).
yA Tensor. Has the same type as x.
y_minA Tensor of type float32.
y_maxA Tensor of type float32.