tf.raw_ops.RequantizePerChannel | TensorFlow v2.16.1 (original) (raw)

tf.raw_ops.RequantizePerChannel

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

Requantizes input with min and max values known per channel.

View aliases

Compat aliases for migration

tf.compat.v1.raw_ops.RequantizePerChannel

tf.raw_ops.RequantizePerChannel(
    input,
    input_min,
    input_max,
    requested_output_min,
    requested_output_max,
    out_type=tf.dtypes.quint8,
    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.
requested_output_min	A Tensor of type float32. The minimum value of the output tensor requested.
requested_output_max	A Tensor of type float32. The maximum value of the output tensor requested.
out_type	An optional tf.DType from: tf.qint8, tf.quint8, tf.qint32, tf.qint16, tf.quint16. Defaults to tf.quint8. The quantized type of output tensor that needs to be converted.
name	A name for the operation (optional).

Returns
A tuple of Tensor objects (output, output_min, output_max).
output	A Tensor of type out_type.
output_min	A Tensor of type float32.
output_max	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.