Adds bias to value.
tf.raw_ops.BiasAddV1(
value, bias, name=None
)
This is a deprecated version of BiasAdd and will be soon removed.
This is a special case of tf.add where bias is restricted to be 1-D.
Broadcasting is supported, so value may have any number of dimensions.
value
Tensor. Must be one of the following types: float32, float64, int32, uint8, int16, int8, complex64, int64, qint8, quint8, qint32, bfloat16, qint16, quint16, uint16, complex128, half, uint32, uint64.
Any number of dimensions.
bias
Tensor. Must have the same type as value.
1-D with size the last dimension of value.
name
Tensor. Has the same type as value.
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.