OneHot

tensorflow C++ API

tensorflow::ops::OneHot

Returns a one-hot tensor.

Summary

The locations represented by indices inindicestake valueon_value, while all other locations take valueoff_value.

If the inputindicesis rankN, the output will have rankN+1, The new axis is created at dimensionaxis(default: the new axis is appended at the end).

Ifindicesis a scalar the output shape will be a vector of lengthdepth.

Ifindicesis a vector of lengthfeatures, the output shape will be: ``` features x depth if axis == -1 depth x features if axis == 0 ```

Ifindicesis a matrix (batch) with shape[batch, features], the output shape will be: ``` batch x features x depth if axis == -1 batch x depth x features if axis == 1 depth x batch x features if axis == 0 ```

Examples

Suppose that

``` indices = [0, 2, -1, 1] depth = 3 on_value = 5.0 off_value = 0.0 axis = -1 ```

Then output is[4 x 3]:

```output =
  [5.0 0.0 0.0]  // one_hot(0)
  [0.0 0.0 5.0]  // one_hot(2)
  [0.0 0.0 0.0]  // one_hot(-1)
  [0.0 5.0 0.0]  // one_hot(1)
```

Suppose that

``` indices = [0, 2, -1, 1] depth = 3 on_value = 0.0 off_value = 3.0 axis = 0 ```

Then output is[3 x 4]:

```output =
  [0.0 3.0 3.0 3.0]
  [3.0 3.0 3.0 0.0]
  [3.0 3.0 3.0 3.0]
  [3.0 0.0 3.0 3.0]
//  ^                one_hot(0)
//      ^            one_hot(2)
//          ^        one_hot(-1)
//              ^    one_hot(1)
```

Suppose that

``` indices = [[0, 2], [1, -1]] depth = 3 on_value = 1.0 off_value = 0.0 axis = -1 ```

Then output is[2 x 2 x 3]:

```output =
  [
    [1.0, 0.0, 0.0]  // one_hot(0)
    [0.0, 0.0, 1.0]  // one_hot(2)
  ][
    [0.0, 1.0, 0.0]  // one_hot(1)
    [0.0, 0.0, 0.0]  // one_hot(-1)
  ]```

Arguments:

• scope: A Scope object
• indices: A tensor of indices.
• depth: A scalar defining the depth of the one hot dimension.
• on_value: A scalar defining the value to fill in output when indices[j] = i .
• off_value: A scalar defining the value to fill in output when indices[j] != i .

Optional attributes (seeAttrs):

• axis: The axis to fill (default: -1, a new inner-most axis).

Returns:

• Output : The one-hot tensor.

OneHot 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 indices: A tensor of indices.
• Input depth: A scalar defining the depth of the one hot dimension.
• Input off_value: A scalar defining the value to fill in output when indices[j] != i .
• Input on_value: A scalar defining the value to fill in output when indices[j] = i .
• OneHot::Attrs attrs: The axis to fill (default: -1, a new inner-most axis).

Output:

• Output output : Output object of OneHot class object.

Result:

• std::vector(Tensor) result_output : A Tensor. have (indices vector size * depth value) shape and indices[N] of index in on_value

Using Method