set_dl_model_paramT_set_dl_model_paramSetDlModelParamSetDlModelParamset_dl_model_param (Operator)
Name
set_dl_model_paramT_set_dl_model_paramSetDlModelParamSetDlModelParamset_dl_model_param — Set the parameters of a deep learning model.
Signature
Description
set_dl_model_paramset_dl_model_paramSetDlModelParamSetDlModelParamset_dl_model_param sets the parameters and hyperparameters
GenParamNameGenParamNameGenParamNamegenParamNamegen_param_name of the deep learning model DLModelHandleDLModelHandleDLModelHandleDLModelHandledlmodel_handle
to the values GenParamValueGenParamValueGenParamValuegenParamValuegen_param_value.
The values GenParamNameGenParamNameGenParamNamegenParamNamegen_param_name can attain, depend on the model type:
There are parameters which can be set for any deep learning model while
others can only be set for specific model types.
A description of the parameters whose value you can only set but not
retrieve is given below. For all other parameters the specific description
is given in get_dl_model_paramget_dl_model_paramGetDlModelParamGetDlModelParamget_dl_model_param.
In get_dl_model_paramget_dl_model_paramGetDlModelParamGetDlModelParamget_dl_model_param we also give an overview,
for which type of model and using which operator a parameter can be set.
In the following we list the parameters GenParamNameGenParamNameGenParamNamegenParamNamegen_param_name you can set
using this operator, set_dl_model_paramset_dl_model_paramSetDlModelParamSetDlModelParamset_dl_model_param.
Thereby, the following symbols denote the model type for which the parameter
can be set and has a possible influence:
-
'Any': any method
-
'3D-GPD': 'type'"type""type""type""type"='3d_gripping_point_detection'"3d_gripping_point_detection""3d_gripping_point_detection""3d_gripping_point_detection""3d_gripping_point_detection"
-
'3D-PE': 'type'"type""type""type""type"='3d_pose_estimation'"3d_pose_estimation""3d_pose_estimation""3d_pose_estimation""3d_pose_estimation"
-
'AD': 'type'"type""type""type""type"='anomaly_detection'"anomaly_detection""anomaly_detection""anomaly_detection""anomaly_detection"
-
'AOD': 'type'"type""type""type""type"='detection'"detection""detection""detection""detection". Advanced Object Detection
-
'CL': 'type'"type""type""type""type"='classification'"classification""classification""classification""classification"
-
'CR-D': 'type'"type""type""type""type"='code_reading_detection'"code_reading_detection""code_reading_detection""code_reading_detection""code_reading_detection"
-
'MLC': 'type'"type""type""type""type"='multi_label_classification'"multi_label_classification""multi_label_classification""multi_label_classification""multi_label_classification"
-
'DC': 'type'"type""type""type""type"='counting'"counting""counting""counting""counting"
-
'OCR-D': 'type'"type""type""type""type"='ocr_detection'"ocr_detection""ocr_detection""ocr_detection""ocr_detection"
-
'OCR-R': 'type'"type""type""type""type"='ocr_recognition'"ocr_recognition""ocr_recognition""ocr_recognition""ocr_recognition"
-
'GC-AD': 'type'"type""type""type""type"='gc_anomaly_detection'"gc_anomaly_detection""gc_anomaly_detection""gc_anomaly_detection""gc_anomaly_detection"
-
'OD': 'type'"type""type""type""type"='detection'"detection""detection""detection""detection"
-
'SE': 'type'"type""type""type""type"='segmentation'"segmentation""segmentation""segmentation""segmentation"
-
'Gen': 'type'"type""type""type""type"='generic'"generic""generic""generic""generic"
- 'adam_beta1'"adam_beta1""adam_beta1""adam_beta1""adam_beta1": 3D-GPD 3D-PE CL OCR-D OCR-R GC-AD AOD OD SE Gen
Moment for linear term in Adam solver. Only applicable if
'solver_type'"solver_type""solver_type""solver_type""solver_type" = 'adam'"adam""adam""adam""adam".
- 'adam_beta2'"adam_beta2""adam_beta2""adam_beta2""adam_beta2": 3D-GPD 3D-PE CL OCR-D OCR-R GC-AD AOD OD SE Gen
Moment for quadratic term in Adam solver. Only applicable if
'solver_type'"solver_type""solver_type""solver_type""solver_type" = 'adam'"adam""adam""adam""adam".
- 'adam_epsilon'"adam_epsilon""adam_epsilon""adam_epsilon""adam_epsilon": 3D-GPD 3D-PE CL OCR-D OCR-R GC-AD AOD OD SE Gen
Epsilon for numeric stability in Adam solver. Only applicable if
'solver_type'"solver_type""solver_type""solver_type""solver_type" = 'adam'"adam""adam""adam""adam".
- 'alignment'"alignment""alignment""alignment""alignment": OCR-R
-
- 'alphabet'"alphabet""alphabet""alphabet""alphabet": OCR-R
-
- 'alphabet_internal'"alphabet_internal""alphabet_internal""alphabet_internal""alphabet_internal": OCR-R
-
- 'alphabet_mapping'"alphabet_mapping""alphabet_mapping""alphabet_mapping""alphabet_mapping": OCR-R
-
- 'anomaly_score_tolerance'"anomaly_score_tolerance""anomaly_score_tolerance""anomaly_score_tolerance""anomaly_score_tolerance": GC-AD
-
- 'backbone_docking_layers'"backbone_docking_layers""backbone_docking_layers""backbone_docking_layers""backbone_docking_layers": CL
The docking layers can be specified for every classifier, also without
using them as backbone.
The specification is only considered for object detection backbones.
- 'batch_size'"batch_size""batch_size""batch_size""batch_size": Any
-
- 'batch_size_multiplier'"batch_size_multiplier""batch_size_multiplier""batch_size_multiplier""batch_size_multiplier": 3D-GPD 3D-PE CL CR-D MLC OCR-D OCR-R GC-AD OD SE Gen
-
- 'batchnorm_momentum'"batchnorm_momentum""batchnorm_momentum""batchnorm_momentum""batchnorm_momentum": Any except DC
-
Calling this option sets the momentum of all batch normalization layers
within the network. The settable values are the same as described in
create_dl_layer_batch_normalizationcreate_dl_layer_batch_normalizationCreateDlLayerBatchNormalizationCreateDlLayerBatchNormalizationcreate_dl_layer_batch_normalization for the parameter
MomentumMomentumMomentummomentummomentum.
Note, if the network has no such layer, nothing is done and therewith
the operation is regarded as successful.
- 'bbox_heads_weight'"bbox_heads_weight""bbox_heads_weight""bbox_heads_weight""bbox_heads_weight", 'class_heads_weight'"class_heads_weight""class_heads_weight""class_heads_weight""class_heads_weight": AOD OD
-
- 'class_ids'"class_ids""class_ids""class_ids""class_ids": 3D-GPD MLC AOD OD SE
-
- 'class_names'"class_names""class_names""class_names""class_names": CL MLC AOD OD SE
-
- 'class_weights'"class_weights""class_weights""class_weights""class_weights": CL
-
- 'complexity'"complexity""complexity""complexity""complexity": AD
-
- 'device'"device""device""device""device": Any
-
- 'enable_resizing'"enable_resizing""enable_resizing""enable_resizing""enable_resizing": Any except DC AOD
-
Calling this option converts certain pooling layers within the
network. More precisely, every non-global pooling layer with a
resulting feature map of size 1x1 is converted into a global pooling
layer. This means, a pooling layer performing e.g., average pooling is
converted into one performing global average pooling.
Note, if this operation is performed, it can not be undone.
Accordingly, you can only call it with the value 'true'"true""true""true""true".
Also, if the network has no such layer, nothing is done and therewith
the operation is regarded as successful.
- 'extract_feature_maps'"extract_feature_maps""extract_feature_maps""extract_feature_maps""extract_feature_maps": CL
-
- 'freeze_backbone_level'"freeze_backbone_level""freeze_backbone_level""freeze_backbone_level""freeze_backbone_level": OD
-
- 'fuse_bn_relu'"fuse_bn_relu""fuse_bn_relu""fuse_bn_relu""fuse_bn_relu": Any except DC
-
Calling this option fuses layer pairs consisting of a batch normalization
layer without activation and a directly connected activation layer
with ReLU activation.
To do so, the output of the batch normalization layer must be used exclusively
as input for the activation layer.
As a result, a batch normalization layer with activation mode ReLU is obtained.
Please note that if this operation is performed, it cannot be undone.
Accordingly, it can only be called with the value 'true'"true""true""true""true".
Also, if the network contains no such fusible layers, no changes are made
and the operation is still considered successful.
Restriction:
Leaky ReLU layers cannot be fused with
batch normalization layers.
- 'fuse_conv_bn'"fuse_conv_bn""fuse_conv_bn""fuse_conv_bn""fuse_conv_bn": Any except DC
-
Calling this option fuses layer pairs consisting of a convolution
layer without activation and a directly connected batch normalization layer.
To do so, the output of the convolution layer must be used exclusively
as input for the batch normalization layer.
As a result, a single convolution layer is obtained that produces
the same output as the original layer pair.
This fusion can improve the runtime performance and memory consumption
of the network during inference.
Please note that if this operation is performed, it cannot be undone.
Accordingly, it can only be called with the value 'true'"true""true""true""true".
Also, if the network contains no such fusible layers, no changes are made
and the operation is still considered successful.
- 'fuse_conv_relu'"fuse_conv_relu""fuse_conv_relu""fuse_conv_relu""fuse_conv_relu": Any except DC
-
Calling this option fuses layer pairs consisting of a convolution
layer without activation and a directly connected activation layer
with ReLU activation.
To do so, the output of the convolution layer must be used exclusively
as input for the activation layer.
As a result, a convolution layer with activation mode ReLU is obtained.
Please note that if this operation is performed, it cannot be undone.
Accordingly, it can only be called with the value 'true'"true""true""true""true".
Also, if the network contains no such fusible layers, no changes are made
and the operation is still considered successful.
Restriction:
Leaky ReLU layers cannot be fused with
convolution layers.
- 'gc_anomaly_networks'"gc_anomaly_networks""gc_anomaly_networks""gc_anomaly_networks""gc_anomaly_networks": GC-AD
-
- 'gpu'"gpu""gpu""gpu""gpu": Any
-
- 'ignore_class_ids'"ignore_class_ids""ignore_class_ids""ignore_class_ids""ignore_class_ids": SE
-
- 'image_dimensions'"image_dimensions""image_dimensions""image_dimensions""image_dimensions": 3D-GPD AD CL CR-D MLC OCR-D OCR-R GC-AD SE AOD
-
- 'image_height'"image_height""image_height""image_height""image_height", 'image_width'"image_width""image_width""image_width""image_width": 3D-GPD AD CL CR-D MLC OCR-D OCR-R GC-AD SE AOD
-
- 'image_num_channels'"image_num_channels""image_num_channels""image_num_channels""image_num_channels": AD CL MLC OCR-D OCR-R GC-AD SE AOD
-
- 'image_range_max'"image_range_max""image_range_max""image_range_max""image_range_max", 'image_range_min'"image_range_min""image_range_min""image_range_min""image_range_min": 3D-GPD OCR-D OCR-R SE AOD
-
- 'image_size'"image_size""image_size""image_size""image_size": 3D-GPD AD CL MLC OCR-D OCR-R GC-AD SE AOD
-
- 'input_dimensions'"input_dimensions""input_dimensions""input_dimensions""input_dimensions": AD CL MLC OCR-D OCR-R SE AOD Gen
-
- 'learning_rate'"learning_rate""learning_rate""learning_rate""learning_rate": 3D-GPD 3D-PE CL MLC OCR-D OCR-R GC-AD AOD OD SE Gen
-
- 'mask_head_weight'"mask_head_weight""mask_head_weight""mask_head_weight""mask_head_weight": OD
This parameter is only available for models with
'instance_segmentation'"instance_segmentation""instance_segmentation""instance_segmentation""instance_segmentation"='true'"true""true""true""true".
- 'max_gradient_norm'"max_gradient_norm""max_gradient_norm""max_gradient_norm""max_gradient_norm": Any
-
- 'max_num_detections'"max_num_detections""max_num_detections""max_num_detections""max_num_detections": AOD CR-D OD
-
- 'max_num_gt'"max_num_gt""max_num_gt""max_num_gt""max_num_gt": AOD
-
- 'max_overlap'"max_overlap""max_overlap""max_overlap""max_overlap": AOD CR-D OD
-
- 'max_overlap_class_agnostic'"max_overlap_class_agnostic""max_overlap_class_agnostic""max_overlap_class_agnostic""max_overlap_class_agnostic": AOD CR-D OD
-
- 'meta_data'"meta_data""meta_data""meta_data""meta_data": Any
-
- 'min_character_score'"min_character_score""min_character_score""min_character_score""min_character_score": OCR-D
-
- 'min_confidence'"min_confidence""min_confidence""min_confidence""min_confidence": MLC AOD CR-D OD
-
- Models of 'type'"type""type""type""type"='detection'"detection""detection""detection""detection":
-
This parameter determines the minimum confidence value a
bounding box prediction must fulfill to count as valid.
This means, when apply_dl_modelapply_dl_modelApplyDlModelApplyDlModelapply_dl_model is called, all output bounding
boxes with a confidence value smaller than 'min_confidence'"min_confidence""min_confidence""min_confidence""min_confidence"
are suppressed.
Usually, a single value for all classes is used. For AOD,
users can also select a minimum confidence threshold for each class.
This can be done by passing a dictionary.
The dictionary must contain the class id to be changed in key
'class_ids' as well as the corresponding min confidence in key 'min_confidences'.
It is possible to only change a subset of all class ids.
Setting a single scalar will overwrite all previous class specific thresholds.
This general usage is demonstrated for instance at the HDevelop example dl_advanced_detection_workflow.hdev.
- 'min_link_score'"min_link_score""min_link_score""min_link_score""min_link_score": OCR-D
-
- 'min_word_area'"min_word_area""min_word_area""min_word_area""min_word_area": OCR-D
-
- 'min_word_score'"min_word_score""min_word_score""min_word_score""min_word_score": OCR-D
-
- 'momentum'"momentum""momentum""momentum""momentum": 3D-GPD 3D-PE CL MLC OCR-D OCR-R GC-AD AOD OD SE Gen
-
Momentum for SGD solver.
Restriction:
Only applicable for 'solver_type'"solver_type""solver_type""solver_type""solver_type" =
'sgd'"sgd""sgd""sgd""sgd".
- 'ood_threshold'"ood_threshold""ood_threshold""ood_threshold""ood_threshold": CL
-
- 'optimize_for_inference'"optimize_for_inference""optimize_for_inference""optimize_for_inference""optimize_for_inference": 3D-GPD 3D-PE CL MLC OCR-D OCR-R GC-AD AOD CR-D OD SE Gen
-
- 'orientation'"orientation""orientation""orientation""orientation": OCR-D
-
- 'patch_size'"patch_size""patch_size""patch_size""patch_size": GC-AD
-
- 'pretrained'"pretrained""pretrained""pretrained""pretrained": Any
-
- 'runtime'"runtime""runtime""runtime""runtime": Any
-
- 'runtime_init'"runtime_init""runtime_init""runtime_init""runtime_init": Any except DC
-
If called with 'immediately'"immediately""immediately""immediately""immediately", the GPU memory is initialized
and the corresponding handle created. Otherwise this is done on
demand, which may result in significantly larger execution times for
the first call of apply_dl_modelapply_dl_modelApplyDlModelApplyDlModelapply_dl_model or
train_dl_model_batchtrain_dl_model_batchTrainDlModelBatchTrainDlModelBatchtrain_dl_model_batch.
If the network architecture is changed subsequently, the GPU memory
is reinitialized.
This can happen e.g., for changes of 'batch_size'"batch_size""batch_size""batch_size""batch_size",
'image_dimensions'"image_dimensions""image_dimensions""image_dimensions""image_dimensions" or 'input_dimensions'"input_dimensions""input_dimensions""input_dimensions""input_dimensions" with
subsequent calls of set_dl_model_paramset_dl_model_paramSetDlModelParamSetDlModelParamset_dl_model_param.
Note, this parameter has no effect if:
-
Running on CPUs, thus if 'runtime'"runtime""runtime""runtime""runtime" is set to 'cpu'"cpu""cpu""cpu""cpu".
-
Running with an AI
2-interface.
-
The device has been set before using 'device'"device""device""device""device".
- 'solver_type'"solver_type""solver_type""solver_type""solver_type": 3D-GPD 3D-PE CL MLC OCR-D OCR-R GC-AD AOD OD SE Gen
-
- 'sort_by_line'"sort_by_line""sort_by_line""sort_by_line""sort_by_line": OCR-D
-
- 'standard_deviation_factor'"standard_deviation_factor""standard_deviation_factor""standard_deviation_factor""standard_deviation_factor": AD
-
- 'tiling'"tiling""tiling""tiling""tiling": OCR-D SE
-
- 'tiling_overlap'"tiling_overlap""tiling_overlap""tiling_overlap""tiling_overlap": OCR-D SE
-
- 'type'"type""type""type""type": Gen
-
This parameter returns the HALCON-specific model type.
Models of 'generic'"generic""generic""generic""generic" fulfill all model functions. But several
deep learning procedures rely a specific 'type'"type""type""type""type".
The value of 'type'"type""type""type""type" can be set from 'generic'"generic""generic""generic""generic" to the
following values:
-
'classification'"classification""classification""classification""classification"
-
'segmentation'"segmentation""segmentation""segmentation""segmentation"
-
'detection'"detection""detection""detection""detection"
Setting a value for 'type'"type""type""type""type", it is checked if the model has all
layers necessary for inference and training. In case of
'detection'"detection""detection""detection""detection", the model must have a BoxProposals-layer. The
resulting model is an object detection model, not advanced object detection.
For other values for 'type'"type""type""type""type" missing necessary layers are added,
if possible.
- 'weight_decay'"weight_decay""weight_decay""weight_decay""weight_decay": 3D-GPD 3D-PE CL OCR-D OCR-R GC-AD AOD OD SE Gen
-
- 'weight_prior'"weight_prior""weight_prior""weight_prior""weight_prior": 3D-GPD 3D-PE CL OCR-D OCR-R GC-AD AOD OD SE Gen
-
Attention
System requirements:
To successfully set 'gpu'"gpu""gpu""gpu""gpu" parameters, cuDNN and cuBLAS are
required, i.e., to set the parameter GenParamNameGenParamNameGenParamNamegenParamNamegen_param_name
'runtime'"runtime""runtime""runtime""runtime" to 'gpu'"gpu""gpu""gpu""gpu".
For further details, please refer to
“Getting started > Setting up HALCON
> System requirements”.
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
DLModelHandleDLModelHandleDLModelHandleDLModelHandledlmodel_handle (input_control) dl_model → HDlModel, HTupleHHandleHTupleHtuple (handle) (IntPtr) (HHandle) (handle)
Handle of the deep learning model.
GenParamNameGenParamNameGenParamNamegenParamNamegen_param_name (input_control) attribute.name → HTuplestrHTupleHtuple (string) (string) (HString) (char*)
Name of the generic parameter.
Default:
'batch_size'
"batch_size"
"batch_size"
"batch_size"
"batch_size"
List of values:
'adam_beta1'"adam_beta1""adam_beta1""adam_beta1""adam_beta1", 'adam_beta2'"adam_beta2""adam_beta2""adam_beta2""adam_beta2", 'adam_epsilon'"adam_epsilon""adam_epsilon""adam_epsilon""adam_epsilon", 'alignment'"alignment""alignment""alignment""alignment", 'alphabet'"alphabet""alphabet""alphabet""alphabet", 'alphabet_internal'"alphabet_internal""alphabet_internal""alphabet_internal""alphabet_internal", 'alphabet_mapping'"alphabet_mapping""alphabet_mapping""alphabet_mapping""alphabet_mapping", 'anchor_angles'"anchor_angles""anchor_angles""anchor_angles""anchor_angles", 'anchor_aspect_ratios'"anchor_aspect_ratios""anchor_aspect_ratios""anchor_aspect_ratios""anchor_aspect_ratios", 'anchor_num_subscales'"anchor_num_subscales""anchor_num_subscales""anchor_num_subscales""anchor_num_subscales", 'anomaly_score_tolerance'"anomaly_score_tolerance""anomaly_score_tolerance""anomaly_score_tolerance""anomaly_score_tolerance", 'backbone'"backbone""backbone""backbone""backbone", 'backbone_docking_layers'"backbone_docking_layers""backbone_docking_layers""backbone_docking_layers""backbone_docking_layers", 'batch_size'"batch_size""batch_size""batch_size""batch_size", 'batch_size_multiplier'"batch_size_multiplier""batch_size_multiplier""batch_size_multiplier""batch_size_multiplier", 'batchnorm_momentum'"batchnorm_momentum""batchnorm_momentum""batchnorm_momentum""batchnorm_momentum", 'bbox_heads_weight'"bbox_heads_weight""bbox_heads_weight""bbox_heads_weight""bbox_heads_weight", 'capacity'"capacity""capacity""capacity""capacity", 'class_heads_weight'"class_heads_weight""class_heads_weight""class_heads_weight""class_heads_weight", 'class_ids'"class_ids""class_ids""class_ids""class_ids", 'class_names'"class_names""class_names""class_names""class_names", 'class_weights'"class_weights""class_weights""class_weights""class_weights", 'complexity'"complexity""complexity""complexity""complexity", 'device'"device""device""device""device", 'enable_resizing'"enable_resizing""enable_resizing""enable_resizing""enable_resizing", 'extract_feature_maps'"extract_feature_maps""extract_feature_maps""extract_feature_maps""extract_feature_maps", 'freeze_backbone_level'"freeze_backbone_level""freeze_backbone_level""freeze_backbone_level""freeze_backbone_level", 'fuse_bn_relu'"fuse_bn_relu""fuse_bn_relu""fuse_bn_relu""fuse_bn_relu", 'fuse_conv_bn'"fuse_conv_bn""fuse_conv_bn""fuse_conv_bn""fuse_conv_bn", 'fuse_conv_relu'"fuse_conv_relu""fuse_conv_relu""fuse_conv_relu""fuse_conv_relu", 'gc_anomaly_networks'"gc_anomaly_networks""gc_anomaly_networks""gc_anomaly_networks""gc_anomaly_networks", 'gpu'"gpu""gpu""gpu""gpu", 'ignore_class_ids'"ignore_class_ids""ignore_class_ids""ignore_class_ids""ignore_class_ids", 'ignore_direction'"ignore_direction""ignore_direction""ignore_direction""ignore_direction", 'image_dimensions'"image_dimensions""image_dimensions""image_dimensions""image_dimensions", 'image_height'"image_height""image_height""image_height""image_height", 'image_num_channels'"image_num_channels""image_num_channels""image_num_channels""image_num_channels", 'image_range_max'"image_range_max""image_range_max""image_range_max""image_range_max", 'image_range_min'"image_range_min""image_range_min""image_range_min""image_range_min", 'image_size'"image_size""image_size""image_size""image_size", 'image_width'"image_width""image_width""image_width""image_width", 'input_dimensions'"input_dimensions""input_dimensions""input_dimensions""input_dimensions", 'instance_type'"instance_type""instance_type""instance_type""instance_type", 'learning_rate'"learning_rate""learning_rate""learning_rate""learning_rate", 'mask_head_weight'"mask_head_weight""mask_head_weight""mask_head_weight""mask_head_weight", 'max_gradient_norm'"max_gradient_norm""max_gradient_norm""max_gradient_norm""max_gradient_norm", 'max_level'"max_level""max_level""max_level""max_level", 'max_num_detections'"max_num_detections""max_num_detections""max_num_detections""max_num_detections", 'max_num_gt'"max_num_gt""max_num_gt""max_num_gt""max_num_gt", 'max_overlap'"max_overlap""max_overlap""max_overlap""max_overlap", 'max_overlap_class_agnostic'"max_overlap_class_agnostic""max_overlap_class_agnostic""max_overlap_class_agnostic""max_overlap_class_agnostic", 'meta_data'"meta_data""meta_data""meta_data""meta_data", 'min_character_score'"min_character_score""min_character_score""min_character_score""min_character_score", 'min_confidence'"min_confidence""min_confidence""min_confidence""min_confidence", 'min_level'"min_level""min_level""min_level""min_level", 'min_link_score'"min_link_score""min_link_score""min_link_score""min_link_score", 'min_word_area'"min_word_area""min_word_area""min_word_area""min_word_area", 'min_word_score'"min_word_score""min_word_score""min_word_score""min_word_score", 'momentum'"momentum""momentum""momentum""momentum", 'num_classes'"num_classes""num_classes""num_classes""num_classes", 'ood_threshold'"ood_threshold""ood_threshold""ood_threshold""ood_threshold", 'optimize_for_inference'"optimize_for_inference""optimize_for_inference""optimize_for_inference""optimize_for_inference", 'orientation'"orientation""orientation""orientation""orientation", 'patch_size'"patch_size""patch_size""patch_size""patch_size", 'pretrained'"pretrained""pretrained""pretrained""pretrained", 'runtime'"runtime""runtime""runtime""runtime", 'runtime_init'"runtime_init""runtime_init""runtime_init""runtime_init", 'solver_type'"solver_type""solver_type""solver_type""solver_type", 'sort_by_line'"sort_by_line""sort_by_line""sort_by_line""sort_by_line", 'standard_deviation_factor'"standard_deviation_factor""standard_deviation_factor""standard_deviation_factor""standard_deviation_factor", 'summary'"summary""summary""summary""summary", 'tiling'"tiling""tiling""tiling""tiling", 'tiling_overlap'"tiling_overlap""tiling_overlap""tiling_overlap""tiling_overlap", 'type'"type""type""type""type", 'weight_decay'"weight_decay""weight_decay""weight_decay""weight_decay", 'weight_prior'"weight_prior""weight_prior""weight_prior""weight_prior"
GenParamValueGenParamValueGenParamValuegenParamValuegen_param_value (input_control) attribute.value(-array) → HTupleMaybeSequence[Union[str, float, int]]HTupleHtuple (integer / string / real) (int / long / string / double) (Hlong / HString / double) (Hlong / char* / double)
Value of the generic parameter.
Default:
1
Suggested values:
1, 2, 3, 50, [80,60], 80, 60, 0.001, -127, 128, 'adam'"adam""adam""adam""adam", 'cpu'"cpu""cpu""cpu""cpu", 'gpu'"gpu""gpu""gpu""gpu", 'immediately'"immediately""immediately""immediately""immediately", 'sgd'"sgd""sgd""sgd""sgd"
Result
If the parameters are valid, the operator
set_dl_model_paramset_dl_model_paramSetDlModelParamSetDlModelParamset_dl_model_param returns the value 2 (
H_MSG_TRUE)
. If
necessary, an exception is raised.
Possible Predecessors
read_dl_modelread_dl_modelReadDlModelReadDlModelread_dl_model,
get_dl_model_paramget_dl_model_paramGetDlModelParamGetDlModelParamget_dl_model_param
Possible Successors
get_dl_model_paramget_dl_model_paramGetDlModelParamGetDlModelParamget_dl_model_param,
apply_dl_modelapply_dl_modelApplyDlModelApplyDlModelapply_dl_model,
train_dl_model_batchtrain_dl_model_batchTrainDlModelBatchTrainDlModelBatchtrain_dl_model_batch,
train_dl_model_anomaly_datasettrain_dl_model_anomaly_datasetTrainDlModelAnomalyDatasetTrainDlModelAnomalyDatasettrain_dl_model_anomaly_dataset
See also
get_dl_model_paramget_dl_model_paramGetDlModelParamGetDlModelParamget_dl_model_param
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:
3D Metrology, Data Code, OCR/OCV, Matching, Deep Learning Enhanced, Deep Learning Professional