DL_ReadCharacters_Deploy


Module: DL_OCR

Loads a deep learning model and prepares its execution on a specific target device.

Name Type Description
Input value
inModelDirectory ReadCharactersModelDirectory* A Read Characters model stored in a specific disk directory. If not set, model is chosen on the basis of inPretrainedModelType.
Input value
inPretrainedModelType OcrPretrainedModel Type of a pretrained model (distributed with Deep Learning Add-on) to deploy. Ignored if inModelDirectory is set.
Input value
inTargetDevice DeviceType* A device selected for deploying and executing the model. If not set, device depending on version (CPU/GPU) of installed Deep Learning Add-on is selected.
Input value
inExecutionHint OcrDeployHint* Prepares the model for an execution with provided settings in advance
Output value
outModelId ReadCharactersModelId Identifier of the deployed model

Hints

  • In most cases, this filter should be placed in the INITIALIZE section.
  • Executing this filter may take several seconds.
  • This filter should be connected to DL_ReadCharacters through the ModelId ports.
  • By default, the model distributed with Deep Learning Add-on will be deployed. If you have a model trained for a specific case, you can set inModelDirectory to it. Please note, that inModelDirectory have to point to existing directory, containing subdirectory named "models", which, in turn, contains file named "model".
  • If inExecutionHint is set to NIL, first execution of DL_ReadCharacters will likely take much more time than following ones. To avoid this, fill inExecutionHint with expected parameters of following calls to DL_ReadCharacters. A size of an analysed area may be obtained from the diagnostic output of DL_ReadCharacters. If you still experience huge performance hit on some calls to DL_ReadCharacters, add another DL_ReadCharacters_Deploy with inExecutionHint filled with parameters from a problematic call to DL_ReadCharacters.

Remarks

  • Passing NIL as inTargetDevice (which is default), is identical to passing DeviceType::CUDA on GPU version of Deep Learning Addon and DeviceType::CPU on CPU version on Deep Learning Addon.
  • GPU version of Deep Learning Addon supports DeviceType::CUDA and DeviceType::CPU as inTargetDevice value.
  • CPU version of Deep Learning Addon supports only DeviceType::CPU as inTargetDevice value.

Complexity Level

This filter is available on Basic Complexity Level.

Disabled in Lite Edition

This filter is disabled in Lite Edition. It is available only in full, Adaptive Vision Studio Professional version.

See Also

  • DL_ReadCharacters – Performs optical character recognition using a pretrained deep learning model.