AIDetectModel (Function)

ONLINE HELP
WINDEV, WEBDEV AND WINDEV MOBILE

Version:

Home | Sign in | English

This content has been translated automatically. Click here to view the French version.

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

WINDEV

WEBDEV

WINDEV Mobile

Others

See also

AIDetectModel (Function)

In french: IAModèleDétecte

Runs a trained neural network model on an image. This function allows you to use artificial intelligence to detect objects in an image.

Caution: This is an advanced function. To use this function, it is recommended to read the documentation of the neural network used (specifics, expected results and interpretation).

Example

// Déclaration de l'image
MonImage is Image
MonImage = IMG_Test

// Déclarer un modèle
MonIAModèleRN is aiNeuralNetworkModel

MonIAModèleRN.Configuration = "MonModel.cfg"
MonIAModèleRN.TrainedWeights = "MonModel.weights.pb"
MonIAModèleRN.PixelScaleFactor = 1.0

// Attention: les dimensions X et Y dépendent du modèle. 
// Si les dimensions spécifiées ne correspondent pas au modèle,
// la fonction IAModèleDétecte renverra une erreur. 
MonIAModèleRN.XDimension = 300 
MonIAModèleRN.YDimension = 300 

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

montabMatrice is array of 1 array of 1 by 1 by 200 by 7 reals

// Exécuter le modèle
montabMatrice = AIDetectModel(MonIAModèleRN, MonImage)

Syntax

<Result> = AIDetectModel(<Model> , <Image>)

<Result>: Array of array

Array of matrices containing the result of the execution of the model.
This array is specific to each model and must be known by the developer.

<Model>: aiNeuralNetworkModel variable

Name of the aiNeuralNetworkModel variable describing the characteristics of the neural network used.
Caution: The various characteristics of this variable are specific to each model and must be known by the developer..

<Image>: String, Image or Image control

Image to be analyzed. This image can correspond to:
a variable of type Image,
the name and path of the image,
the name and path of a PDF file,
an Image memo item,
an Image control.

Remarks

The AI engine used by AIDetectModel is OpenCV. This engine reads the AI models and executes them.
The supported neural network models are:
- caffe,
- tensorflow,
- darknet,
- onnx
The model must be trained (weights are known).
The expected extensions according to the models are:
- Configuration:
  - Caffe: *.prototxt
  - Tensorflow: *.pbtxt
  - Darknet: *.cfg
- Weight:
  - Caffe: *.caffemodel
  - Tensorflow: *.pb
  - Darknet: *.weights
  - Open Neural Network Exchange (ONNX): *.onnx

Business / UI classification: Business Logic

Component: wd300ia.dll