tf.nn.bias_add(
value,
bias,
data_format=None,
name=None
)
Defined in tensorflow/python/ops/nn_ops.py
.
Adds bias
to value
.
This is (mostly) a special case of tf.add
where bias
is restricted to 1-D.
Broadcasting is supported, so value
may have any number of dimensions.
Unlike tf.add
, the type of bias
is allowed to differ from value
in the
case where both types are quantized.
Args:
value
: ATensor
with typefloat
,double
,int64
,int32
,uint8
,int16
,int8
,complex64
, orcomplex128
.bias
: A 1-DTensor
with size matching the last dimension ofvalue
. Must be the same type asvalue
unlessvalue
is a quantized type, in which case a different quantized type may be used.data_format
: A string. 'NHWC' and 'NCHW' are supported.name
: A name for the operation (optional).
Returns:
A Tensor
with the same type as value
.