get_dl_model_layer_weightsGetDlModelLayerWeightsGetDlModelLayerWeightsget_dl_model_layer_weightsT_get_dl_model_layer_weights🔗

Short description🔗

get_dl_model_layer_weightsGetDlModelLayerWeightsGetDlModelLayerWeightsget_dl_model_layer_weightsT_get_dl_model_layer_weights — Get the weights (or values) of a Deep Learning model layer.

Signature🔗

get_dl_model_layer_weights( out image Weights, dl_model DLModelHandle, string LayerName, string WeightsType )

Description🔗

The operator get_dl_model_layer_weightsGetDlModelLayerWeights returns in Weightsweightsweights the values of a LayerNamelayerNamelayer_name of the model DLModelHandleDLModelHandledlmodel_handle.

The parameter WeightsTypeweightsTypeweights_type determines which type of layer values are retrieved. The following values are supported for WeightsTypeweightsTypeweights_type:

'batchnorm_mean'"batchnorm_mean": Batch-wise calculated mean values to normalize the inputs. For further information, please refer to create_dl_layer_batch_normalizationCreateDlLayerBatchNormalization.

Restriction: This value is only supported if the layer is of type 'batchnorm'"batchnorm".
'batchnorm_mean_avg'"batchnorm_mean_avg": Average of the batch-wise calculated mean values to normalize the inputs. For further information, please refer to create_dl_layer_batch_normalizationCreateDlLayerBatchNormalization.

Restriction: This value is only supported if the layer is of type 'batchnorm'"batchnorm".
'batchnorm_variance'"batchnorm_variance": Batch-wise calculated variance values to normalize the inputs. For further information, please refer to create_dl_layer_batch_normalizationCreateDlLayerBatchNormalization.

Restriction: This value is only supported if the layer is of type 'batchnorm'"batchnorm".
'batchnorm_variance_avg'"batchnorm_variance_avg": Average of the batch-wise calculated variance values to normalize the inputs. For further information, please refer to create_dl_layer_batch_normalizationCreateDlLayerBatchNormalization.

Restriction: This value is only supported if the layer is of type 'batchnorm'"batchnorm".
'bias'"bias": Biases of the layer.
'bias_gradient'"bias_gradient": Gradients of the biases of the layer.
'bias_gradient_norm_l2'"bias_gradient_norm_l2": Gradients of the biases of the layer in terms of L2 norm.
'bias_norm_l2'"bias_norm_l2": Biases of the layer in terms of L2 norm.
'bias_update'"bias_update": Update of the biases of the layer. This is used in e.g., a solver which uses the last update.
'bias_update_norm_l2'"bias_update_norm_l2": Update of the biases of the layer in terms of L2 norm. This is used in a solver which uses the last update.
'weights'"weights": Weights of the layer.
'weights_gradient'"weights_gradient": Gradients of the weights of the layer.
'weights_gradient_norm_l2'"weights_gradient_norm_l2": Gradients of the weights of the layer in terms of L2 norm.
'weights_norm_l2'"weights_norm_l2": Weights of the layer in terms of L2 norm.
'weights_update'"weights_update": Update of the weights of the layer. This is used in a solver which uses the last update.
'weights_update_norm_l2'"weights_update_norm_l2": Update of the weights of the layer in terms of L2 norm. This is used in a solver which uses the last update.

The following tables give an overview, which parameters for WeightsTypeweightsTypeweights_type can be set using set_dl_model_layer_weightsSetDlModelLayerWeights and which ones can be retrieved using get_dl_model_layer_weightsGetDlModelLayerWeights.

Layer Parameters	`set`	`get`
'batchnorm_mean'"batchnorm_mean"	`x`	`x`
'batchnorm_mean_avg'"batchnorm_mean_avg"	`x`	`x`
'batchnorm_variance'"batchnorm_variance"	`x`	`x`
'batchnorm_variance_avg'"batchnorm_variance_avg"	`x`	`x`
'bias'"bias"	`x`	`x`
'bias_gradient'"bias_gradient"		`x`
'bias_gradient_norm_l2'"bias_gradient_norm_l2"		`x`
'bias_norm_l2'"bias_norm_l2"		`x`
'bias_update'"bias_update"		`x`
'bias_update_norm_l2'"bias_update_norm_l2"		`x`
'weights'"weights"	`x`	`x`
'weights_gradient'"weights_gradient"		`x`
'weights_gradient_norm_l2'"weights_gradient_norm_l2"		`x`
'weights_norm_l2'"weights_norm_l2"		`x`
'weights_update'"weights_update"		`x`
'weights_update_norm_l2'"weights_update_norm_l2"		`x`

Attention🔗

The operator get_dl_model_layer_weightsGetDlModelLayerWeights is only applicable to self-created networks. For networks delivered by HALCON, the operator returns an empty tuple.

Execution information🔗

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🔗

Weightsweightsweights (output_object) image(-array) → object (real)HObject (real)HImage (real)HObject (real)Hobject * (real)

Output weights.

DLModelHandleDLModelHandledlmodel_handle (input_control) dl_model → (handle)HTuple (HHandle)HDlModel, HTuple (IntPtr)HHandleHtuple (handle)

Handle of the deep learning model.

LayerNamelayerNamelayer_name (input_control) string → (string)HTuple (HString)HTuple (string)strHtuple (char*)

Name of the layer to be queried.

WeightsTypeweightsTypeweights_type (input_control) string → (string)HTuple (HString)HTuple (string)strHtuple (char*)

Selected type of layer values to be returned.

Default: 'weights'"weights"
List of values: 'batchnorm_mean', 'batchnorm_mean_avg', 'batchnorm_variance', 'batchnorm_variance_avg', 'bias', 'bias_gradient', 'bias_gradient_norm_l2', 'bias_norm_l2', 'bias_update', 'bias_update_norm_l2', 'weights', 'weights_gradient', 'weights_gradient_norm_l2', 'weights_norm_l2', 'weights_update', 'weights_update_norm_l2'

Example🔗

(HDevelop)

set_system ('seed_rand', 42)
* Create a small model network.
create_dl_layer_input ('input', [InputImageSize[0],InputImageSize[1],1], [],\
                       [], DLGraphNodeInput)
create_dl_layer_convolution (DLGraphNodeInput, 'conv', 3, 1, 1, 2, 1, 'none',\
                             'none', [], [], DLGraphNodeConvolution)
create_dl_layer_activation (DLGraphNodeConvolution, 'relu', 'relu', [], [],\
                            DLGraphNodeActivation)
create_dl_layer_dense (DLGraphNodeActivation, 'dense', 3, [], [],\
                       DLGraphNodeDense)
create_dl_layer_softmax (DLGraphNodeDense, 'softmax', [], [],\
                          DLGraphNodeSoftMax)
create_dl_model (DLGraphNodeSoftMax, DLModelHandle)
*
set_dl_model_param (DLModelHandle, 'type', 'classification')
set_dl_model_param (DLModelHandle, 'batch_size', 1)
set_dl_model_param (DLModelHandle, 'runtime', 'gpu')
set_dl_model_param (DLModelHandle, 'runtime_init', 'immediately')
*
* Train for 5 iterations.
for TrainIterations := 1 to NumTrainIterations by 1
    train_dl_model_batch (DLModelHandle, DLSample, DLTrainResult)
endfor
*
* Get the gradients, weights, and activations.
get_dl_model_layer_gradients (GradientsSoftmax, DLModelHandle, 'softmax')
get_dl_model_layer_gradients (GradientsDense, DLModelHandle, 'dense')
get_dl_model_layer_gradients (GradientsConv, DLModelHandle, 'conv')
*
get_dl_model_layer_weights (WeightsDense, DLModelHandle, 'dense',\
                      'weights_gradient')
get_dl_model_layer_weights (WeightsConv, DLModelHandle, 'conv',\
                      'weights_gradient')
*
get_dl_model_layer_activations (ActivationsDense,  DLModelHandle, 'dense')
get_dl_model_layer_activations (ActivationsConv,  DLModelHandle, 'conv')

Combinations with other operators🔗

Combinations

Possible predecessors

create_dl_modelCreateDlModel, train_dl_model_batchTrainDlModelBatch, set_dl_model_layer_weightsSetDlModelLayerWeights

Possible successors

set_dl_model_layer_weightsSetDlModelLayerWeights

Alternatives

get_dl_model_layer_activationsGetDlModelLayerActivations, get_dl_model_layer_gradientsGetDlModelLayerGradients

Module🔗

This operator uses dynamic licensing (see the ‘Installation Guide’). Which of the following modules is required depends on the specific usage of the operator:

Deep Learning Professional