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_paramSetDlModelParamSetDlModelParamSetDlModelParamset_dl_model_param
sets the parameters and hyperparameters
GenParamNameGenParamNameGenParamNameGenParamNamegenParamNamegen_param_name
of the deep learning model DLModelHandleDLModelHandleDLModelHandleDLModelHandleDLModelHandledlmodel_handle
to the values GenParamValueGenParamValueGenParamValueGenParamValuegenParamValuegen_param_value
.
The values GenParamNameGenParamNameGenParamNameGenParamNamegenParamNamegen_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_paramGetDlModelParamGetDlModelParamGetDlModelParamget_dl_model_param
.
In get_dl_model_paramget_dl_model_paramGetDlModelParamGetDlModelParamGetDlModelParamget_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 GenParamNameGenParamNameGenParamNameGenParamNamegenParamNamegen_param_name
you can set
using this operator, set_dl_model_paramset_dl_model_paramSetDlModelParamSetDlModelParamSetDlModelParamset_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
-
'AD': 'type'"type""type""type""type""type"='anomaly_detection'"anomaly_detection""anomaly_detection""anomaly_detection""anomaly_detection""anomaly_detection"
-
'CL': 'type'"type""type""type""type""type"='classification'"classification""classification""classification""classification""classification"
-
'OD': 'type'"type""type""type""type""type"='detection'"detection""detection""detection""detection""detection"
-
'SE': 'type'"type""type""type""type""type"='segmentation'"segmentation""segmentation""segmentation""segmentation""segmentation"
-
'Gen': 'type'"type""type""type""type""type"='generic'"generic""generic""generic""generic""generic"
- Applicable to several model types
-
- 'batch_size'"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""batch_size_multiplier": CL OD SE
-
- 'class_ids'"class_ids""class_ids""class_ids""class_ids""class_ids": OD SE
-
- 'device'"device""device""device""device""device": Any
-
- 'enable_resizing'"enable_resizing""enable_resizing""enable_resizing""enable_resizing""enable_resizing": Any
-
Calling this option, converts pooling certain 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.
For more information about pooling layer and possible modes of operation,
see the “Solution Guide on Classification”
.
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""true".
Also, if the network has no such layer, nothing is done and therewith
the operation is regarded as successful.
- 'fuse_conv_relu'"fuse_conv_relu""fuse_conv_relu""fuse_conv_relu""fuse_conv_relu""fuse_conv_relu": Any
-
Calling this option, fuses layer pairs consisting of a convolution
layer without activation and a directly connected activation layer
with ReLU activation.
In order to so do, the output of the convolution layer is only used
as input for the activation layer.
As a result a convolution layer with activation mode ReLU is obtained.
For more information about layers and possible modes of operation,
see the “Solution Guide on Classification”
.
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""true".
Also, if the network has no such fusible layers, nothing is done and
therewith the operation is regarded as successful.
- 'fuse_bn_relu'"fuse_bn_relu""fuse_bn_relu""fuse_bn_relu""fuse_bn_relu""fuse_bn_relu": Any
-
Calling this option, fuses layer pairs consisting of a batch normalization
layer without activation and a directly connected activation layer
with ReLU activation.
In order to so do, the output of the batch normalization layer is only used
as input for the activation layer.
As a result a batch normalization layer with activation mode ReLU is obtained.
For more information about layers and possible modes of operation,
see the “Solution Guide on Classification”
.
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""true".
Also, if the network has no such fusible layers, nothing is done and
therewith the operation is regarded as successful.
- 'gpu'"gpu""gpu""gpu""gpu""gpu": Any
-
- 'image_dimensions'"image_dimensions""image_dimensions""image_dimensions""image_dimensions""image_dimensions": AD CL SE
-
- 'image_height'"image_height""image_height""image_height""image_height""image_height", 'image_width'"image_width""image_width""image_width""image_width""image_width": AN CL SE
-
- 'image_num_channels'"image_num_channels""image_num_channels""image_num_channels""image_num_channels""image_num_channels": AD CL SE
-
- 'input_dimensions'"input_dimensions""input_dimensions""input_dimensions""input_dimensions""input_dimensions": AD CL SE
-
- 'learning_rate'"learning_rate""learning_rate""learning_rate""learning_rate""learning_rate": CL OD SE
-
- 'meta_data'"meta_data""meta_data""meta_data""meta_data""meta_data": Any
-
- 'momentum'"momentum""momentum""momentum""momentum""momentum": CL OD SE
-
- 'optimize_for_inference'"optimize_for_inference""optimize_for_inference""optimize_for_inference""optimize_for_inference""optimize_for_inference": CL OD SE
-
- 'precision'"precision""precision""precision""precision""precision": Any
-
- 'precision_is_converted'"precision_is_converted""precision_is_converted""precision_is_converted""precision_is_converted""precision_is_converted": Any
-
- 'runtime'"runtime""runtime""runtime""runtime""runtime": Any
-
- 'runtime_init'"runtime_init""runtime_init""runtime_init""runtime_init""runtime_init": Any
-
If called with 'immediately'"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_modelApplyDlModelApplyDlModelApplyDlModelapply_dl_model
or
train_dl_model_batchtrain_dl_model_batchTrainDlModelBatchTrainDlModelBatchTrainDlModelBatchtrain_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""batch_size",
'image_dimensions'"image_dimensions""image_dimensions""image_dimensions""image_dimensions""image_dimensions" or 'input_dimensions'"input_dimensions""input_dimensions""input_dimensions""input_dimensions""input_dimensions" with
subsequent calls of set_dl_model_paramset_dl_model_paramSetDlModelParamSetDlModelParamSetDlModelParamset_dl_model_param
.
Note, this parameter has no effect if:
-
Running on CPUs, thus if 'runtime'"runtime""runtime""runtime""runtime""runtime" is set to 'cpu'"cpu""cpu""cpu""cpu""cpu".
-
Running with an AI2-interface.
-
The device has been set before using 'device'"device""device""device""device""device".
- 'weight_prior'"weight_prior""weight_prior""weight_prior""weight_prior""weight_prior": CL OD SE
-
- Models of 'type'"type""type""type""type""type"='anomaly_detection'"anomaly_detection""anomaly_detection""anomaly_detection""anomaly_detection""anomaly_detection"
-
- 'complexity'"complexity""complexity""complexity""complexity""complexity"
-
- 'standard_deviation_factor'"standard_deviation_factor""standard_deviation_factor""standard_deviation_factor""standard_deviation_factor""standard_deviation_factor"
-
- Models of 'type'"type""type""type""type""type"='classification'"classification""classification""classification""classification""classification"
-
- 'backbone_docking_layers'"backbone_docking_layers""backbone_docking_layers""backbone_docking_layers""backbone_docking_layers""backbone_docking_layers"
The docking layers can be specified for every classifier, also without
using them as backbone.
The specification is only considered for object detection backbones.
- 'class_names'"class_names""class_names""class_names""class_names""class_names"
-
- 'extract_feature_maps'"extract_feature_maps""extract_feature_maps""extract_feature_maps""extract_feature_maps""extract_feature_maps"
-
- Models of 'type'"type""type""type""type""type"='detection'"detection""detection""detection""detection""detection"
-
- 'freeze_backbone_level'"freeze_backbone_level""freeze_backbone_level""freeze_backbone_level""freeze_backbone_level""freeze_backbone_level"
-
- 'max_num_detections'"max_num_detections""max_num_detections""max_num_detections""max_num_detections""max_num_detections"
-
- 'max_overlap'"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""max_overlap_class_agnostic"
-
- 'min_confidence'"min_confidence""min_confidence""min_confidence""min_confidence""min_confidence"
-
- Models of 'type'"type""type""type""type""type"='segmentation'"segmentation""segmentation""segmentation""segmentation""segmentation"
-
- 'ignore_class_ids'"ignore_class_ids""ignore_class_ids""ignore_class_ids""ignore_class_ids""ignore_class_ids"
-
- 'image_range_max'"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_range_min"
-
- Models of 'type'"type""type""type""type""type"='generic'"generic""generic""generic""generic""generic"
-
- 'type'"type""type""type""type""type"
Change the type of a generic model.
Some models read from the ONNX format are not recognized as models of
type 'classification'"classification""classification""classification""classification""classification".
By setting 'type'"type""type""type""type""type" to 'classification'"classification""classification""classification""classification""classification", a SoftMax layer
is appended and the model can be trained.
All other usage of this parameter is unsupported and may
corrupt your model.
Attention
System requirements:
To successfully set 'gpu'"gpu""gpu""gpu""gpu""gpu" parameters, cuDNN and cuBLAS are
required, i.e., to set the parameter GenParamNameGenParamNameGenParamNameGenParamNamegenParamNamegen_param_name
'runtime'"runtime""runtime""runtime""runtime""runtime" to 'gpu'"gpu""gpu""gpu""gpu""gpu".
For further details, please refer to the “Installation Guide”
,
paragraph “Requirements for Deep Learning and Deep-Learning-Based Methods”.
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
DLModelHandleDLModelHandleDLModelHandleDLModelHandleDLModelHandledlmodel_handle
(input_control) dl_model →
HDlModel, HTupleHHandleHTupleHtuple (handle) (IntPtr) (HHandle) (handle)
Handle of the deep learning model.
GenParamNameGenParamNameGenParamNameGenParamNamegenParamNamegen_param_name
(input_control) attribute.name →
HTuplestrHTupleHtuple (string) (string) (HString) (char*)
Name of the generic parameter.
Default value:
'learning_rate'
"learning_rate"
"learning_rate"
"learning_rate"
"learning_rate"
"learning_rate"
List of values: 'alphabet'"alphabet""alphabet""alphabet""alphabet""alphabet", 'anchor_angles'"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_aspect_ratios", 'anchor_num_subscales'"anchor_num_subscales""anchor_num_subscales""anchor_num_subscales""anchor_num_subscales""anchor_num_subscales", 'backbone'"backbone""backbone""backbone""backbone""backbone", 'backbone_docking_layers'"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", 'batch_size_multiplier'"batch_size_multiplier""batch_size_multiplier""batch_size_multiplier""batch_size_multiplier""batch_size_multiplier", 'bbox_heads_weight'"bbox_heads_weight""bbox_heads_weight""bbox_heads_weight""bbox_heads_weight""bbox_heads_weight", 'capacity'"capacity""capacity""capacity""capacity""capacity", 'class_heads_weight'"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_ids", 'class_names'"class_names""class_names""class_names""class_names""class_names", 'class_weights'"class_weights""class_weights""class_weights""class_weights""class_weights", 'complexity'"complexity""complexity""complexity""complexity""complexity", 'device'"device""device""device""device""device", 'enable_resizing'"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""extract_feature_maps", 'freeze_backbone_level'"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_bn_relu", 'fuse_conv_relu'"fuse_conv_relu""fuse_conv_relu""fuse_conv_relu""fuse_conv_relu""fuse_conv_relu", 'gpu'"gpu""gpu""gpu""gpu""gpu", 'ignore_class_ids'"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""ignore_direction", 'image_dimensions'"image_dimensions""image_dimensions""image_dimensions""image_dimensions""image_dimensions", 'image_height'"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_num_channels", 'image_range_max'"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_range_min", 'image_width'"image_width""image_width""image_width""image_width""image_width", 'input_dimensions'"input_dimensions""input_dimensions""input_dimensions""input_dimensions""input_dimensions", 'instance_type'"instance_type""instance_type""instance_type""instance_type""instance_type", 'learning_rate'"learning_rate""learning_rate""learning_rate""learning_rate""learning_rate", 'max_level'"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_detections", 'max_overlap'"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""max_overlap_class_agnostic", 'meta_data'"meta_data""meta_data""meta_data""meta_data""meta_data", 'min_confidence'"min_confidence""min_confidence""min_confidence""min_confidence""min_confidence", 'min_level'"min_level""min_level""min_level""min_level""min_level", 'momentum'"momentum""momentum""momentum""momentum""momentum", 'num_classes'"num_classes""num_classes""num_classes""num_classes""num_classes", 'optimize_for_inference'"optimize_for_inference""optimize_for_inference""optimize_for_inference""optimize_for_inference""optimize_for_inference", 'runtime'"runtime""runtime""runtime""runtime""runtime", 'runtime_init'"runtime_init""runtime_init""runtime_init""runtime_init""runtime_init", 'standard_deviation_factor'"standard_deviation_factor""standard_deviation_factor""standard_deviation_factor""standard_deviation_factor""standard_deviation_factor", 'summary'"summary""summary""summary""summary""summary", 'type'"type""type""type""type""type", 'weight_prior'"weight_prior""weight_prior""weight_prior""weight_prior""weight_prior"
GenParamValueGenParamValueGenParamValueGenParamValuegenParamValuegen_param_value
(input_control) attribute.value(-array) →
HTupleMaybeSequence[Union[str, float, int]]HTupleHtuple (real / string / integer) (double / string / int / long) (double / HString / Hlong) (double / char* / Hlong)
Value of the generic parameter.
Default value: 0.001
Suggested values: 1, 2, 3, 50, [80,60], 80, 60, 0.001, -127, 128, 'cpu'"cpu""cpu""cpu""cpu""cpu", 'gpu'"gpu""gpu""gpu""gpu""gpu", 'immediately'"immediately""immediately""immediately""immediately""immediately"
Result
If the parameters are valid, the operator
set_dl_model_paramset_dl_model_paramSetDlModelParamSetDlModelParamSetDlModelParamset_dl_model_param
returns the value TRUE. If
necessary, an exception is raised.
Possible Predecessors
read_dl_modelread_dl_modelReadDlModelReadDlModelReadDlModelread_dl_model
,
get_dl_model_paramget_dl_model_paramGetDlModelParamGetDlModelParamGetDlModelParamget_dl_model_param
Possible Successors
get_dl_model_paramget_dl_model_paramGetDlModelParamGetDlModelParamGetDlModelParamget_dl_model_param
,
apply_dl_modelapply_dl_modelApplyDlModelApplyDlModelApplyDlModelapply_dl_model
,
train_dl_model_batchtrain_dl_model_batchTrainDlModelBatchTrainDlModelBatchTrainDlModelBatchtrain_dl_model_batch
,
train_dl_model_anomaly_datasettrain_dl_model_anomaly_datasetTrainDlModelAnomalyDatasetTrainDlModelAnomalyDatasetTrainDlModelAnomalyDatasettrain_dl_model_anomaly_dataset
See also
get_dl_model_paramget_dl_model_paramGetDlModelParamGetDlModelParamGetDlModelParamget_dl_model_param
Module
Deep Learning Inference