tf.nn.bias_add( value, bias, data_format=None, name=None )
See the guide: Neural Network > Activation Functions
This is (mostly) a special case of
bias is restricted to 1-D.
Broadcasting is supported, so
value may have any number of dimensions.
tf.add, the type of
bias is allowed to differ from
value in the
case where both types are quantized.
bias: A 1-D
Tensorwith size matching the last dimension of
value. Must be the same type as
valueis 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).
Tensor with the same type as