aiNeuralNetworkModel (Variable type)

ONLINE HELP
WINDEV, WEBDEV AND WINDEV MOBILE

Version:

Home | Sign in | English

Help / WLanguage / WLanguage functions / Standard functions / Image detection functions

Properties specific to aiNeuralNetworkModel variables

WINDEV

WEBDEV

WINDEV Mobile

Others

See also

aiNeuralNetworkModel (Variable type)

In french: iaModèleRéseauDeNeurones

The aiNeuralNetworkModel type is used to define all the advanced characteristics of a neural network used by AIDetectModel. You can define and change the characteristics of this neural network using different WLanguage properties.

Remark: For more details on the declaration of this type of variable and the use of WLanguage properties, see Declaring a variable.

Example

// Image declaration
MyImage is Image
MyImage = IMG_Test

// Declare a model
MyAINNModel is aiNeuralNetworkModel

MyAINNModel.Configuration = "MyModel.cfg"
MyAINNModel.TrainedWeights = "MyModel.weights.pb"
MyAINNModel.PixelScaleFactor = 1.0

// Caution: the X and Y dimensions depend on the model. 
// If the specified dimensions do not match the model,
// AIDetectModel returns an error. 
MyAINNModel.XDimension = 300 
MyAINNModel.YDimension = 300 

MyAINNModel.AverageIntensityR = 104
MyAINNModel.AverageIntensityG = 117
MyAINNModel.AverageIntensityB = 113
MyAINNModel.RGBColor = True

myMatrixArray is array of 1 array of 1 by 1 by 200 by 7 real

// Run model
myMatrixArray = AIDetectModel(MyAINNModel, MyImage)

Remarks

Properties specific to aiNeuralNetworkModel variables

The following properties can be used to handle a neural network model:

Property name	Type used	Effect

AverageIntensityB	Integer	Average intensity of the Blue (B) color in the training data. This property is optional.
AverageIntensityG	Integer	Average intensity of the Green (G) color in the training data. This property is optional.
AverageIntensityR	Integer	Average intensity of the Red (R) color in the training data. This property is optional.
Configuration	Character string	Full path of the file that contains the configuration of the model. Remark: The possible types of configurations are: Caffe: .prototxt Tensorflow: .pbtxt Darknet: *.cfg
OutputLayerName	Character string	Name of the output neural network layer.
PixelScaleFactor	Real	Used to scale pixel values. Set to 1.0 by default (no scaling).
RGBColor	Boolean	True if the provided images are encoded in RGB. In this case, the conversion to BGR encoding will be done automatically. False (default value) if the provided images are encoded in BGR. This property is optional.
TrainedWeights	Character string	Full path of the file that contains the trained weights of the model. Remark: The possible types of weights are: Caffe: .caffemodel Tensorflow: .pb Darknet: .weights Open Neural Network Exchange (ONNX): .onnx
TransposeRequired	Boolean	if transposition is required, False otherwise. When to use this property? OpenCV creates matrices based on images and defines them as "Number of columns, Number of rows, Number of channels". Some models expect matrices with the following format: "Number of channels, Number of columns, Number of rows". This means it is necessary to modify the matrix representation of the image created by OpenCV.
XDimension	Integer	Image size required by the model: X value. By default, this property corresponds to the width of the image.
YDimension	Integer	Image size required by the model: Y value. By default, this property corresponds to the height of the image.