AiliaDetectorModel Class Reference

Inheritance diagram for AiliaDetectorModel:

Collaboration diagram for AiliaDetectorModel:

Public Member Functions
bool	Settings (uint set_format, uint set_channel, uint set_range, uint set_algorithm, uint set_category_n, uint set_flag)
	Set up the model. More...
bool	Anchors (float [] anchors)
	Set the anchors (anchors or biases) information for YoloV2 and others. More...
bool	SetInputShape (uint x, uint y)
	Sets the input geometry for YoloV3 and YOLOX. More...
override bool	OpenFile (string prototxt, string model_path)
	Create a network object from a model file. More...
override bool	OpenEx (Ailia.ailiaFileCallback callback, IntPtr arg1, IntPtr arg2)
	Creates a network object from a file callback. More...
override bool	OpenMem (byte[] prototxt_buf, byte[] model_buf)
	Creates network objects from memory. More...
List< AiliaDetector.AILIADetectorObject >	ComputeFromImage (Color32 [] image, int tex_width, int tex_height, float threshold, float iou)
	Detection from images and obtaining results. More...
List< AiliaDetector.AILIADetectorObject >	ComputeFromImageB2T (Color32 [] image, int tex_width, int tex_height, float threshold, float iou)
	Detection from bottom-top images and obtaining results. More...
override void	Close ()
	Discard the detection object. More...
override void	Dispose ()
	Release resources. More...
Public Member Functions inherited from AiliaModel
bool	Environment (int type)
	Selects the specified type of calculation environment. More...
string	EnvironmentName ()
	Displays the name of the selected environment. More...
int	GetEnvironmentCount ()
	Get the number of available computing environments (CPU, GPU). More...
Ailia.AILIAEnvironment	GetEnvironment (int idx)
	Obtains the computing environment for the specified index. More...
bool	SelectEnvironment (int idx)
	Select the calculation environment. More...
Ailia.AILIAEnvironment	GetSelectedEnvironment ()
	Retrieves the selected computing environment. More...
void	SetMemoryMode (uint set_memory_mode)
	Sets the memory mode. More...
void	DisableLayerFusion ()
	Disables speedup due to layer fusion. More...
bool	Predict (float[] output_data, float[] input_data)
	Perform inference and obtain inference results. More...
Ailia.AILIAShape	GetInputShape ()
uint []	GetInputShapeND ()
	Obtains the shape of the input data at the time of inference. More...
bool	SetInputShape (Ailia.AILIAShape shape)
	Sets the shape of the input data during inference. More...
bool	SetInputShapeND (uint[] shape, int dim)
	Change the shape of the input data during inference. More...
Ailia.AILIAShape	GetOutputShape ()
	Obtains the shape of the output data during inference. More...
uint []	GetOutputShapeND ()
	Obtains the shape of the output data during inference. More...
Ailia.AILIAShape	GetBlobShape (string layer_name)
	Obtains the shape (layer format) of the internal data (Blob) at the time of inference. (Obsolete) More...
int	FindBlobIndexByName (string name)
	Look up and retrieve the index of the internal data (Blob) at the time of inference by name. More...
Ailia.AILIAShape	GetBlobShape (uint idx)
	Obtains the shape (layer format) of the internal data (Blob) at the time of inference. More...
Ailia.AILIAShape	GetBlobShape (int idx)
bool	GetBlobData (float[] output_data, uint idx)
	Obtains internal data (Blob) at the time of inference. More...
bool	GetBlobData (float[] output_data, int idx)
bool	SetInputBlobData (float[] input_data, uint idx)
	Set input data to the specified Blob. More...
bool	SetInputBlobData (float[] input_data, int idx)
bool	SetInputBlobShape (Ailia.AILIAShape shape, uint idx)
	Sets the format of the specified input data (Blob). (4 dimensions or less) More...
bool	SetInputBlobShape (Ailia.AILIAShape shape, int idx)
bool	SetInputBlobShapeND (uint[] shape, uint dim, uint idx)
	Sets the format of the input data (Blob). (5D or more) More...
bool	SetInputBlobShapeND (uint[] shape, int dim, int idx)
uint []	GetInputBlobList ()
	Obtains a list of the indices of the input data (Blob). More...
uint []	GetOutputBlobList ()
	Obtains a list of indices of the output data (Blob). More...
bool	CopyBlobData (uint dst_blob_idx, uint src_blob_idx, AiliaModel src_model=null)
	Perform copies between blobs that specified. More...
bool	Update ()
	Inference is performed with pre-populated data. More...
string	GetStatusString (int status)
	Returns a string corresponding to the status code. More...
string	GetErrorDetail ()
	Returns error details. More...
bool	SetProfileMode (uint profile_mode)
	Enable profile mode. More...
string	GetSummary ()
	Obtain network information and profile results. More...

Protected Member Functions
override void	Dispose (bool disposing)

Additional Inherited Members
Protected Attributes inherited from AiliaModel
IntPtr	ailia = IntPtr.Zero
bool	logging = true
Properties inherited from AiliaModel
int	Status [get, protected set]
	Status code Get the library status code. More...

Member Function Documentation

Anchors()

bool AiliaDetectorModel.Anchors ( float []  anchors )

inline

Set the anchors (anchors or biases) information for YoloV2 and others.

Parameters

anchors

Dimensions of the anchors (possible shape, height and width of the detection box)

Returns

Returns true on success, false on failure.

AiliaDetector.ailiaDetectorSetAnchors() sets the anchors (anchors or biases) information for YoloV2 and others. YoloV2, for example, tries to detect multiple default shapes of a box at the same time. This data describes the information of the multiple forms of the box. The anchors are stored in the form {x,y,x,y...} The nchors are stored in the form {x,y,x,y...}.

                                         {
        UInt32 anchors_count=(UInt32)(anchors.Length/2);
        if (ailia_detector == IntPtr.Zero) {
            if(logging){
                Debug.Log("ailia_detector must be opened");
            }
            return false;
        }
        int status=AiliaDetector.ailiaDetectorSetAnchors(ailia_detector,anchors,anchors_count);
        if(status!=Ailia.AILIA_STATUS_SUCCESS){
            if(logging){
                Debug.Log("ailiaDetectorSetAnchors failed "+status);
            }
            return false;
        }
        return true;
    }

Close()

override void AiliaDetectorModel.Close ( )

inlinevirtual

Discard the detection object.

Returns

Return nothing

Destroys the detection object.

Reimplemented from AiliaModel.

                                {
        if(ailia_detector!=IntPtr.Zero){
            AiliaDetector.ailiaDestroyDetector(ailia_detector);
            ailia_detector=IntPtr.Zero;
        }
        base.Close();
    }

ComputeFromImage()

List<AiliaDetector.AILIADetectorObject> AiliaDetectorModel.ComputeFromImage ( Color32 []  image, int  tex_width, int  tex_height, float  threshold, float  iou  )

inline

Detection from images and obtaining results.

Parameters

image	Input Image
tex_width	Image width
tec_height	Image height
threadhold	Detection threshold (e.g., 0.1f) (the smaller the threshold, the easier it is to detect and the greater the number of detections)
iou	Duplicate exclusion threshold (e.g., 0.45f) (the smaller the threshold, the less duplicates are tolerated and the fewer the number of detections)

Returns

List of detected objects.

Inference is made from the given image and the results of inference are retrieved in a list.

                                                                                                                                            {
        return ComputeFromImageWithFormat(image,tex_width,tex_height,threshold,iou,AiliaFormat.AILIA_IMAGE_FORMAT_RGBA);
    }

ComputeFromImageB2T()

List<AiliaDetector.AILIADetectorObject> AiliaDetectorModel.ComputeFromImageB2T ( Color32 []  image, int  tex_width, int  tex_height, float  threshold, float  iou  )

inline

Detection from bottom-top images and obtaining results.

Parameters

image	Input image
tex_width	Image width
tec_height	Image height
threadhold	Detection threshold (e.g., 0.1f) (the smaller the threshold, the easier it is to detect and the greater the number of detections)
iou	Duplicate exclusion threshold (e.g., 0.45f) (the smaller the threshold, the less duplicates are tolerated and the fewer the number of detections)

Returns

List of detected objects.

Inference is made from the given image and the results of inference are retrieved in a list.

                                                                                                                                               {
        return ComputeFromImageWithFormat(image,tex_width,tex_height,threshold,iou,AiliaFormat.AILIA_IMAGE_FORMAT_RGBA_B2T);
    }

Dispose() [1/2]

override void AiliaDetectorModel.Dispose ( )

inlinevirtual

Release resources.

Reimplemented from AiliaModel.

    {
        Dispose(true);
    }

Dispose() [2/2]

override void AiliaDetectorModel.Dispose ( bool  disposing )

inlineprotectedvirtual

Reimplemented from AiliaModel.

    {
        if (disposing){
            // release managed resource
        }
        Close(); // release unmanaged resource
        base.Dispose(disposing);
    }

OpenEx()

override bool AiliaDetectorModel.OpenEx ( Ailia.ailiaFileCallback  callback, IntPtr  arg1, IntPtr  arg2  )

inlinevirtual

Creates a network object from a file callback.

Parameters

callback	User-defined file access callback function structure
alg1	Argument pointer notified to AILIA_USER_API_FOPEN
arg2	Argument pointer notified to AILIA_USER_API_FOPEN

Returns

If this function is successful, it returns true , or false otherwise.

　Creates a network object from a file callback.

Reimplemented from AiliaModel.

                                                                                         {
        Close();
        bool status=base.OpenEx(callback,arg1,arg2);
        if(!status){
            if(logging){
                Debug.Log("ailiaModelOpenEx failed");
            }
            return false;
        }
        return OpenDetector();
    }

OpenFile()

override bool AiliaDetectorModel.OpenFile ( string  prototxt, string  model_path  )

inlinevirtual

Create a network object from a model file.

Parameters

prototxt	Path name of the prototxt file (MBSC or UTF16)
model_path	Pathname of the protobuf/onnx file (MBSC or UTF16)

Returns

If this function is successful, it returns true , or false otherwise.

Create a network object from a model file.

Reimplemented from AiliaModel.

                                                                    {
        Close();
        bool status=base.OpenFile(prototxt,model_path);
        if(!status){
            if(logging){
                Debug.Log("ailiaModelOpenFile failed");
            }
            return false;
        }
        return OpenDetector();
    }

OpenMem()

override bool AiliaDetectorModel.OpenMem ( byte []  prototxt_buf, byte []  model_buf  )

inlinevirtual

Creates network objects from memory.

Parameters

prototxt_buf	Pointer to data in prototxt file
model_buf	Pointer to data in protobuf/onnx file

Returns

If this function is successful, it returns true , or false otherwise.

Creates network objects from memory.

Reimplemented from AiliaModel.

                                                                      {
        Close();
        bool status=base.OpenMem(prototxt_buf,model_buf);
        if(!status){
            if(logging){
                Debug.Log("ailiaModelOpenMem failed");
            }
            return false;
        }
        return OpenDetector();
    }

SetInputShape()

bool AiliaDetectorModel.SetInputShape ( uint  x, uint  y  )

inline

Sets the input geometry for YoloV3 and YOLOX.

Parameters

x	Model input image width
y	Model input image height

Returns

Return ture on success, false on failure.

AiliaDetector.ailiaDetectorSetInputShape() allows you to specify the input image size for the model in YoloV3 and YOLOX.

YoloV3 and YOLOX allows a single model to support any input resolution. (with a multiple limit of 32) Use this API when specifying the input image size to the model, for example, to reduce computational complexity. It must be executed between Open() and Compute(). If this API is not executed, the default of 416x416 is used. If executed outside of YOLOv3, returns AILIA_STATUS_INVALID_STATE

                                            {
        if (ailia_detector == IntPtr.Zero) {
            if(logging){
                Debug.Log("ailia_detector must be opened");
            }
            return false;
        }
        int status=AiliaDetector.ailiaDetectorSetInputShape(ailia_detector,x,y); 
        if(status!=Ailia.AILIA_STATUS_SUCCESS){
            if(logging){
                Debug.Log("ailiaDetectorSetInputShape failed "+status);
            }
            return false;
        }
        return true;
    }

Settings()

bool AiliaDetectorModel.Settings ( uint  set_format, uint  set_channel, uint  set_range, uint  set_algorithm, uint  set_category_n, uint  set_flag  )

inline

Set up the model.

Parameters

set_format	Network image format
set_channel	Network channel format
set_range	Netwoek range
set_algorithm	Algorithm
set_category	Number of categories to be recognized
set_flag	Flag

Returns

Returns true when configuration is complete.

Set up the model.

                                                                                                                              {
        format=set_format;
        channel=set_channel;
        range=set_range;
        algorithm=set_algorithm;
        category_n=set_category_n;
        flag=set_flag;
        return true;
    }

---

The documentation for this class was generated from the following file:

• AiliaDetectorModel.cs