TensorOperatorWrapper

public class TensorOperatorWrapper

The adapter that makes a TensorOperator able to run with TensorImage.

See Also

• TensorOperator
• TensorImage

Public Constructors

| | TensorOperatorWrapper(TensorOperator op) Wraps a TensorOperator object as an ImageOperator, so that the TensorOperator could handle TensorImage objects by handling its underlying TensorBuffer.

|

Public Methods

| TensorImage | apply(TensorImage image) | | int | getOutputImageHeight(int inputImageHeight, int inputImageWidth) Computes the height of the expected output image when input image size is given.

| | int | getOutputImageWidth(int inputImageHeight, int inputImageWidth) Computes the width of the expected output image when input image size is given.

| | PointF | inverseTransform(PointF point, int inputImageHeight, int inputImageWidth) Transforms a point from coordinates system of the result image back to the one of the input image.

|

Inherited Methods

From class java.lang.Object

| boolean | equals(Object arg0) | | final Class<?> | getClass() | | int | hashCode() | | final void | notify() | | final void | notifyAll() | | String | toString() | | final void | wait(long arg0, int arg1) | | final void | wait(long arg0) | | final void | wait() |

From interface org.tensorflow.lite.support.image.ImageOperator

| abstract TensorImage | apply(TensorImage image) | | abstract int | getOutputImageHeight(int inputImageHeight, int inputImageWidth) Computes the height of the expected output image when input image size is given.

| | abstract int | getOutputImageWidth(int inputImageHeight, int inputImageWidth) Computes the width of the expected output image when input image size is given.

| | abstract PointF | inverseTransform(PointF point, int inputImageHeight, int inputImageWidth) Transforms a point from coordinates system of the result image back to the one of the input image.

|

From interface org.tensorflow.lite.support.common.Operator

| abstract TensorImage | apply(TensorImage x) Applies an operation on a T object, returning a T object.

|

Public Constructors

public TensorOperatorWrapper (TensorOperator op)

Wraps a TensorOperator object as an ImageOperator, so that the TensorOperator could handle TensorImage objects by handling its underlying TensorBuffer.

Requirement: The op should not change coordinate system when applied on an image.

Parameters

| op | The created operator. |

Public Methods

public TensorImage apply (TensorImage image)

Parameters

| image | |

public int getOutputImageHeight (int inputImageHeight, int inputImageWidth)

Computes the height of the expected output image when input image size is given.

Parameters

| inputImageHeight | | | inputImageWidth | |

public int getOutputImageWidth (int inputImageHeight, int inputImageWidth)

Computes the width of the expected output image when input image size is given.

Parameters

| inputImageHeight | | | inputImageWidth | |

public PointF inverseTransform (PointF point, int inputImageHeight, int inputImageWidth)

Transforms a point from coordinates system of the result image back to the one of the input image.

Parameters

| point | the point from the result coordinates system. | | inputImageHeight | the height of input image. | | inputImageWidth | the width of input image. |

Returns

• the point with the coordinates from the coordinates system of the input image.