get_dl_model_layer_weightsT_get_dl_model_layer_weightsGetDlModelLayerWeightsGetDlModelLayerWeightsget_dl_model_layer_weights (Operator)

Name

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

Signature

Description

The operator get_dl_model_layer_weightsget_dl_model_layer_weightsGetDlModelLayerWeightsGetDlModelLayerWeightsGetDlModelLayerWeightsget_dl_model_layer_weights returns in WeightsWeightsWeightsWeightsweightsweights the values of a LayerNameLayerNameLayerNameLayerNamelayerNamelayer_name of the model DLModelHandleDLModelHandleDLModelHandleDLModelHandleDLModelHandledlmodel_handle.

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

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

  Restriction: This value is only supported if the layer is of type 'batchnorm'"batchnorm""batchnorm""batchnorm""batchnorm""batchnorm".

• 'batchnorm_mean_avg'"batchnorm_mean_avg""batchnorm_mean_avg""batchnorm_mean_avg""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_normalizationcreate_dl_layer_batch_normalizationCreateDlLayerBatchNormalizationCreateDlLayerBatchNormalizationCreateDlLayerBatchNormalizationcreate_dl_layer_batch_normalization.

  Restriction: This value is only supported if the layer is of type 'batchnorm'"batchnorm""batchnorm""batchnorm""batchnorm""batchnorm".

• 'batchnorm_variance'"batchnorm_variance""batchnorm_variance""batchnorm_variance""batchnorm_variance""batchnorm_variance": Batch-wise calculated variance values to normalize the inputs. For further information, please refer to create_dl_layer_batch_normalizationcreate_dl_layer_batch_normalizationCreateDlLayerBatchNormalizationCreateDlLayerBatchNormalizationCreateDlLayerBatchNormalizationcreate_dl_layer_batch_normalization.

  Restriction: This value is only supported if the layer is of type 'batchnorm'"batchnorm""batchnorm""batchnorm""batchnorm""batchnorm".

• 'batchnorm_variance_avg'"batchnorm_variance_avg""batchnorm_variance_avg""batchnorm_variance_avg""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_normalizationcreate_dl_layer_batch_normalizationCreateDlLayerBatchNormalizationCreateDlLayerBatchNormalizationCreateDlLayerBatchNormalizationcreate_dl_layer_batch_normalization.

  Restriction: This value is only supported if the layer is of type 'batchnorm'"batchnorm""batchnorm""batchnorm""batchnorm""batchnorm".

• 'bias'"bias""bias""bias""bias""bias": Biases of the layer.

• 'bias_gradient'"bias_gradient""bias_gradient""bias_gradient""bias_gradient""bias_gradient": Gradients of the biases of the layer.

• 'bias_gradient_norm_l2'"bias_gradient_norm_l2""bias_gradient_norm_l2""bias_gradient_norm_l2""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""bias_norm_l2""bias_norm_l2""bias_norm_l2""bias_norm_l2": Biases of the layer in terms of L2 norm.

• 'bias_update'"bias_update""bias_update""bias_update""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""bias_update_norm_l2""bias_update_norm_l2""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""weights""weights""weights": Weights of the layer.

• 'weights_gradient'"weights_gradient""weights_gradient""weights_gradient""weights_gradient""weights_gradient": Gradients of the weights of the layer.

• 'weights_gradient_norm_l2'"weights_gradient_norm_l2""weights_gradient_norm_l2""weights_gradient_norm_l2""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_norm_l2""weights_norm_l2""weights_norm_l2""weights_norm_l2": Weights of the layer in terms of L2 norm.

• 'weights_update'"weights_update""weights_update""weights_update""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""weights_update_norm_l2""weights_update_norm_l2""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 WeightsTypeWeightsTypeWeightsTypeWeightsTypeweightsTypeweights_type can be set using set_dl_model_layer_weightsset_dl_model_layer_weightsSetDlModelLayerWeightsSetDlModelLayerWeightsSetDlModelLayerWeightsset_dl_model_layer_weights and which ones can be retrieved using get_dl_model_layer_weightsget_dl_model_layer_weightsGetDlModelLayerWeightsGetDlModelLayerWeightsGetDlModelLayerWeightsget_dl_model_layer_weights.

Attention

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

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

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')

Possible Predecessors

create_dl_modelcreate_dl_modelCreateDlModelCreateDlModelCreateDlModelcreate_dl_model, train_dl_classifier_batchtrain_dl_classifier_batchTrainDlClassifierBatchTrainDlClassifierBatchTrainDlClassifierBatchtrain_dl_classifier_batch, set_dl_model_layer_weightsset_dl_model_layer_weightsSetDlModelLayerWeightsSetDlModelLayerWeightsSetDlModelLayerWeightsset_dl_model_layer_weights

Possible Successors

set_dl_model_layer_weightsset_dl_model_layer_weightsSetDlModelLayerWeightsSetDlModelLayerWeightsSetDlModelLayerWeightsset_dl_model_layer_weights

Alternatives

get_dl_model_layer_activationsget_dl_model_layer_activationsGetDlModelLayerActivationsGetDlModelLayerActivationsGetDlModelLayerActivationsget_dl_model_layer_activations, get_dl_model_layer_gradientsget_dl_model_layer_gradientsGetDlModelLayerGradientsGetDlModelLayerGradientsGetDlModelLayerGradientsget_dl_model_layer_gradients

Module

Foundation. 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 Training