tf.nn.bias_add
tf.nn.bias_add
tf.nn.bias_add
bias_add( value, bias, data_format=None, name=None )
Defined in tensorflow/python/ops/nn_ops.py
.
See the guide: Neural Network > Activation Functions
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
.
© 2017 The TensorFlow Authors. All rights reserved.
Licensed under the Creative Commons Attribution License 3.0.
Code samples licensed under the Apache 2.0 License.
https://www.tensorflow.org/api_docs/python/tf/nn/bias_add