tf.raw_ops.QuantizedAdd

Returns x + y element-wise, working on quantized buffers.

Compat aliases for migration

tf.compat.v1.raw_ops.QuantizedAdd

tf.raw_ops.QuantizedAdd(
    x,
    y,
    min_x,
    max_x,
    min_y,
    max_y,
    Toutput=tf.dtypes.qint32,
    name=None
)

Args
`x`	A `Tensor`. Must be one of the following types: `qint8`, `quint8`, `qint32`, `qint16`, `quint16`.
`y`	A `Tensor`. Must be one of the following types: `qint8`, `quint8`, `qint32`, `qint16`, `quint16`.
`min_x`	A `Tensor` of type `float32`. The float value that the lowest quantized `x` value represents.
`max_x`	A `Tensor` of type `float32`. The float value that the highest quantized `x` value represents.
`min_y`	A `Tensor` of type `float32`. The float value that the lowest quantized `y` value represents.
`max_y`	A `Tensor` of type `float32`. The float value that the highest quantized `y` value represents.
`Toutput`	An optional `tf.DType` from: `tf.qint8, tf.quint8, tf.qint32, tf.qint16, tf.quint16`. Defaults to `tf.qint32`.
`name`	A name for the operation (optional).

Returns
A tuple of `Tensor` objects (z, min_z, max_z).
`z`	A `Tensor` of type `Toutput`.
`min_z`	A `Tensor` of type `float32`.
`max_z`	A `Tensor` of type `float32`.

Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates. Some content is licensed under the numpy license.

Last updated 2024-04-26 UTC.

tf.raw_ops.QuantizedAdd Stay organized with collections Save and categorize content based on your preferences.