create_dl_layer_zoom_sizeT_create_dl_layer_zoom_sizeCreateDlLayerZoomSizeCreateDlLayerZoomSizecreate_dl_layer_zoom_size (Operator)

Name

create_dl_layer_zoom_sizeT_create_dl_layer_zoom_sizeCreateDlLayerZoomSizeCreateDlLayerZoomSizecreate_dl_layer_zoom_size — Create a zoom layer using an absolute output size.

Signatur

Beschreibung

The operator create_dl_layer_zoom_sizecreate_dl_layer_zoom_sizeCreateDlLayerZoomSizeCreateDlLayerZoomSizeCreateDlLayerZoomSizecreate_dl_layer_zoom_size creates a zoom layer using an absolute output size and returns the layer handle in DLLayerZoomDLLayerZoomDLLayerZoomDLLayerZoomDLLayerZoomdllayer_zoom.

The parameter DLLayerInputDLLayerInputDLLayerInputDLLayerInputDLLayerInputdllayer_input determines the feeding input layer and expects the layer handle as value.

The parameter LayerNameLayerNameLayerNameLayerNamelayerNamelayer_name sets an individual layer name. Note that if creating a model using create_dl_modelcreate_dl_modelCreateDlModelCreateDlModelCreateDlModelcreate_dl_model each layer of the created network must have an unique name.

The parameters WidthWidthWidthWidthwidthwidth and HeightHeightHeightHeightheightheight define the absolute output size of the zoom layer DLLayerZoomDLLayerZoomDLLayerZoomDLLayerZoomDLLayerZoomdllayer_zoom.

The parameter InterpolationInterpolationInterpolationInterpolationinterpolationinterpolation defines the interpolation mode. Currently only 'bilinear'"bilinear""bilinear""bilinear""bilinear""bilinear" interpolation is supported.

The parameter AlignCornersAlignCornersAlignCornersAlignCornersalignCornersalign_corners defines how coordinates are transformed from the output to the input image:

'true'"true""true""true""true""true":

The transformation is applied on the HALCON Non-Standard Cartesian coordinate system (edge-centered, with the origin in the upper left corner, see chapter Transformationen / 2D-Transformationen). Using the axis as an example, this leads to:

'false'"false""false""false""false""false":

The transformation is applied in the HALCON standard coordinate system (pixel centered, with the origin in the center of the upper left pixel, see chapter Transformationen / 2D-Transformationen). Using the axis as an example, this leads to:

Note that this parameter applies only to InterpolationInterpolationInterpolationInterpolationinterpolationinterpolation 'bilinear'"bilinear""bilinear""bilinear""bilinear""bilinear".

The following generic parameters GenParamNameGenParamNameGenParamNameGenParamNamegenParamNamegen_param_name and the corresponding values GenParamValueGenParamValueGenParamValueGenParamValuegenParamValuegen_param_value are supported:

'is_inference_output'"is_inference_output""is_inference_output""is_inference_output""is_inference_output""is_inference_output":

Determines whether apply_dl_modelapply_dl_modelApplyDlModelApplyDlModelApplyDlModelapply_dl_model will include the output of this layer in the dictionary DLResultBatchDLResultBatchDLResultBatchDLResultBatchDLResultBatchdlresult_batch even without specifying this layer in OutputsOutputsOutputsOutputsoutputsoutputs ('true'"true""true""true""true""true") or not ('false'"false""false""false""false""false").

Default: 'false'"false""false""false""false""false"

'num_trainable_params'"num_trainable_params""num_trainable_params""num_trainable_params""num_trainable_params""num_trainable_params":

Number of trainable parameters (weights and biases) of the layer.

Certain parameters of layers created using this operator create_dl_layer_zoom_sizecreate_dl_layer_zoom_sizeCreateDlLayerZoomSizeCreateDlLayerZoomSizeCreateDlLayerZoomSizecreate_dl_layer_zoom_size can be set and retrieved using further operators. The following tables give an overview, which parameters can be set using set_dl_model_layer_paramset_dl_model_layer_paramSetDlModelLayerParamSetDlModelLayerParamSetDlModelLayerParamset_dl_model_layer_param and which ones can be retrieved using get_dl_model_layer_paramget_dl_model_layer_paramGetDlModelLayerParamGetDlModelLayerParamGetDlModelLayerParamget_dl_model_layer_param or get_dl_layer_paramget_dl_layer_paramGetDlLayerParamGetDlLayerParamGetDlLayerParamget_dl_layer_param. Note, the operators set_dl_model_layer_paramset_dl_model_layer_paramSetDlModelLayerParamSetDlModelLayerParamSetDlModelLayerParamset_dl_model_layer_param and get_dl_model_layer_paramget_dl_model_layer_paramGetDlModelLayerParamGetDlModelLayerParamGetDlModelLayerParamget_dl_model_layer_param require a model created by create_dl_modelcreate_dl_modelCreateDlModelCreateDlModelCreateDlModelcreate_dl_model.

Ausführungsinformationen

• Multithreading-Typ: reentrant (läuft parallel zu nicht-exklusiven Operatoren).
• Multithreading-Bereich: global (kann von jedem Thread aufgerufen werden).
• Wird ohne Parallelisierung verarbeitet.

Parameter

Alternativen

create_dl_layer_zoom_factorcreate_dl_layer_zoom_factorCreateDlLayerZoomFactorCreateDlLayerZoomFactorCreateDlLayerZoomFactorcreate_dl_layer_zoom_factor, create_dl_layer_zoom_to_layer_sizecreate_dl_layer_zoom_to_layer_sizeCreateDlLayerZoomToLayerSizeCreateDlLayerZoomToLayerSizeCreateDlLayerZoomToLayerSizecreate_dl_layer_zoom_to_layer_size

Modul

Deep Learning Training