ExpandDims

tensorflow C++ API

tensorflow::ops::ExpandDims

Inserts a dimension of 1 into a tensor's shape.

Summary

Given a tensorinput, this operation inserts a dimension of 1 at the dimension indexaxisofinput's shape. The dimension indexaxisstarts at zero; if you specify a negative number foraxisit is counted backward from the end.

This operation is useful if you want to add a batch dimension to a single element. For example, if you have a single image of shape[height, width, channels], you can make it a batch of 1 image withexpand_dims(image, 0), which will make the shape[1, height, width, channels].

Other examples:

``` 't' is a tensor of shape [2]

shape(expand_dims(t, 0)) ==> [1, 2] shape(expand_dims(t, 1)) ==> [2, 1] shape(expand_dims(t, -1)) ==> [2, 1]

't2' is a tensor of shape [2, 3, 5]

shape(expand_dims(t2, 0)) ==> [1, 2, 3, 5] shape(expand_dims(t2, 2)) ==> [2, 3, 1, 5] shape(expand_dims(t2, 3)) ==> [2, 3, 5, 1] ```

This operation requires that:

-1-input.dims() <= dim <= input.dims()

This operation is related tosqueeze(), which removes dimensions of size 1.

Arguments:

• scope: A Scope object
• axis: 0-D (scalar). Specifies the dimension index at which to expand the shape of input

Returns:

• Output: Contains the same data as input, but its shape has an additional dimension of size 1 added.

ExpandDims block

Source link :https://github.com/EXPNUNI/enuSpaceTensorflow/blob/master/enuSpaceTensorflow/tf_array_ops.cpp

Argument:

• Scope scope : A Scope object (A scope is generated automatically each page. A scope is not connected.)
• Input input: A N-D Tensor .
• Input axis : 0-D (scalar). Specifies the dimension index at which to expand the shape of input.

Return:

• Output output : Output object of ExpandDims class object.

Result:

• std::vector(Tensor) result_output : A Tensorwith the same data as input, but its shape has an additional dimension of size 1 added.

Using Method

※ 차원을 증가 시킨다.