Operator Reference

HALCON Operator Reference / Deep Learning / Framework
ClassesClasses | | Operators

get_dl_model_layer_activationsT_get_dl_model_layer_activationsGetDlModelLayerActivationsGetDlModelLayerActivationsget_dl_model_layer_activations (Operator)

get_dl_model_layer_activationsT_get_dl_model_layer_activationsGetDlModelLayerActivationsGetDlModelLayerActivationsget_dl_model_layer_activations — Get the activations of a Deep Learning model layer.

Signature

get_dl_model_layer_activations( : Activations : DLModelHandle, LayerName : )

Herror T_get_dl_model_layer_activations(Hobject* Activations, const Htuple DLModelHandle, const Htuple LayerName)

void GetDlModelLayerActivations(HObject* Activations, const HTuple& DLModelHandle, const HTuple& LayerName)

HImage HDlModel::GetDlModelLayerActivations(const HString& LayerName) const

HImage HDlModel::GetDlModelLayerActivations(const char* LayerName) const

HImage HDlModel::GetDlModelLayerActivations(const wchar_t* LayerName) const   ( Windows only)

static void HOperatorSet.GetDlModelLayerActivations(out HObject activations, HTuple DLModelHandle, HTuple layerName)

HImage HDlModel.GetDlModelLayerActivations(string layerName)

def get_dl_model_layer_activations(dlmodel_handle: HHandle, layer_name: str) -> HObject

Description

The operator get_dl_model_layer_activationsget_dl_model_layer_activationsGetDlModelLayerActivationsGetDlModelLayerActivationsget_dl_model_layer_activations returns in ActivationsActivationsActivationsactivationsactivations the activations of the specified LayerNameLayerNameLayerNamelayerNamelayer_name of the model DLModelHandleDLModelHandleDLModelHandleDLModelHandledlmodel_handle.

ActivationsActivationsActivationsactivationsactivations is a tuple of batch_size many objects, where every object is an image having the size (width, height, depth) of the given LayerNameLayerNameLayerNamelayerNamelayer_name.

Execution Information

  • Multithreading type: reentrant (runs in parallel with non-exclusive operators).
  • Multithreading scope: global (may be called from any thread).
  • Processed without parallelization.

Parameters

ActivationsActivationsActivationsactivationsactivations (output_object)  image(-array) → objectHImageHObjectHObjectHobject * (real)

Output activations.

DLModelHandleDLModelHandleDLModelHandleDLModelHandledlmodel_handle (input_control)  dl_model → HDlModel, HTupleHHandleHTupleHtuple (handle) (IntPtr) (HHandle) (handle)

Handle of the deep learning model.

LayerNameLayerNameLayerNamelayerNamelayer_name (input_control)  string → HTuplestrHTupleHtuple (string) (string) (HString) (char*)

Name of the layer to be queried.

Module

Deep Learning Professional

ClassesClasses | | Operators