FB_VN_WriteMlModel

FB_VN_WriteMlModel 1:

This FB writes a machine learning model to the hard drive.

Syntax

Definition:

FUNCTION_BLOCK FB_VN_WriteMlModel
VAR_INPUT
    ipMlModel : Reference To ITcVnMlModel;
    sFilePath : STRING;
    bWrite    : BOOL;
    nTimeout  : TIME;
END_VAR
VAR_OUTPUT
    bBusy     : BOOL;
    bError    : BOOL;
    nErrorId  : UDINT;
END_VAR

FB_VN_WriteMlModel 2: Inputs

Name

Type

Default

Description

ipMlModel

Reference To ITcVnMlModel

 

The machine learning model to write

sFilePath

STRING

 

Full path of the file or relative path to the default directory on the target pc (e.g. only a file name). If the string is empty, a file name will be generated (containing the current time).

bWrite

BOOL

 

Writing the machine learning model is triggered by a rising edge at this input.

nTimeout

TIME

VISION_ADS_TIMEOUT

Indicates the time before the function is cancelled.

FB_VN_WriteMlModel 3: Outputs

Name

Type

Description

bBusy

BOOL

This output remains TRUE until the function block has executed a command, but at the longest for the duration supplied to the 'nTimeout' input. While bBusy = TRUE, no new command will be accepted at the inputs.

bError

BOOL

This output is switched to TRUE as soon as an error occurs during the execution of a command. The command-specific error code is contained in ‘nErrorId’. If the function block has a timeout error, 'bError' is TRUE and 'nErrorId' is 1861 (hexadecimal 0x745). Is reset to FALSE by the execution of a command at the inputs.

nErrorId

UDINT

Contains the ADS error code or the command-specific error code of the last executed command. Is reset to 0 by the execution of a command at the inputs.

Weiterführende Informationen

Der Funktionsblock FB_VN_WriteMlModel speichert ein ML-Modell aus der SPS asynchron in einer Datei.

Parameter

Einige Parameter sind zentral im Kapitel File Access Parameter beschrieben.

ML-Modell

Das ML-Modell ipMlModel wird unter dem angegebenen Dateipfad im Binärformat gespeichert.

Einen Sonderfall stellt das Speichern eines ITcVnColorModel dar, da dieses zuerst noch mit der folgenden Zeile in ein ML-Modell gewandelt werden muss. Alternativ kann Color Model auch durch das ITcVnMlModel mit den entsprechenden Funktionen ersetzt werden.

hr := ipColorModel.TcQueryInterface(IID_ITcVnMlModel, ADR(ipWriteMlModel));

Dateipfad und Format

Wenn sFilePath leer ist, wird ein Dateiname mit der aktuellen Zeit generiert und die Endung vmlm verwendet.

Anwendung

Das Speichern eines ML-Models in die Datei C:\TcVision\MlModel.vmlm sieht z. B. so aus:

fbWriteMlModel(
    ipMlModel    := ipWriteMlModel,
    sFilePath    := 'C:\TcVision\MlModel.vmlm',
    bWrite       := TRUE,
    nTimeout     := T#500MS);

IF NOT fbWriteMlModel.bBusy AND NOT fbWriteMlModel.bError THEN
    // Ml-Model was written successfully to file
END_IF

Verwandter Funktionsblock: FB_VN_ReadMlModel.

Required License

TC3 Vision Base

System Requirements

Development environment

Target platform

PLC libraries to include

TwinCAT V3.1. 4024.44 or later

PC or CX (x64) with PL50, e.g. Intel 4-core Atom CPU

Tc3_Vision