BiasAdd
tensorflow C++ API
Addsbias
tovalue
.
Summary
This is a special case oftf.add
wherebias
is restricted to be 1-D. Broadcasting is supported, sovalue
may have any number of dimensions.
Arguments:
- scope: A Scope objectA
- value:Any number of dimensions.
- bias: 1-D with size the last dimension of
value
.
Optional attributes (seeAttrs
):
- data_format: Specify the data format of the input and output data. With the default format "NHWC", the bias tensor will be added to the last dimension of the value tensor. Alternatively, the format could be "NCHW", the data storage order of: [batch, in_channels, in_height, in_width]. The tensor will be added to "in_channels", the third-to-the-last dimension.
Returns:
Output
: Broadcasted sum ofvalue
andbias
.
BiasAdd block
Source link : https://github.com/EXPNUNI/enuSpaceTensorflow/blob/master/enuSpaceTensorflow/tf_nn.cpp
Argument:
- Scope scope : A Scope object (A scope is generated automatically each page. A scope is not connected.)
- Input value: connect Input node.
- Input bias: connect Input node.
- BiasAdd ::Attrs attrs : Input attrs in value. ex) data_format_ = NHWC;
Return:
- Output output : Output object of BiasAdd class object.
Result:
- std::vector(Tensor) result_output : Returned object of executed result by calling session.