read_dl_modelT_read_dl_modelReadDlModelReadDlModelread_dl_model (Operator)
Name
read_dl_modelT_read_dl_modelReadDlModelReadDlModelread_dl_model — Read a deep learning model from a file.
Signature
Description
The operator read_dl_modelread_dl_modelReadDlModelReadDlModelReadDlModelread_dl_model reads a deep learning model.
Such models have to be in the HALCON format or in the ONNX format
(see the reference below). Restrictions apply to the latter.
As a result, the handle DLModelHandleDLModelHandleDLModelHandleDLModelHandleDLModelHandledlmodel_handle is returned.
The model is loaded from the file FileNameFileNameFileNameFileNamefileNamefile_name.
This file is thereby searched in the directory $HALCONROOT/dl/
as well as in the currently used directory.
The default HALCON file extension for deep learning networks is
'.hdl'".hdl"".hdl"".hdl"".hdl"".hdl".
Please note that the values of runtime specific parameters are not written
to file, see write_dl_modelwrite_dl_modelWriteDlModelWriteDlModelWriteDlModelwrite_dl_model.
As a consequence, when reading a model, these parameters are initialized
with their default value, see get_dl_model_paramget_dl_model_paramGetDlModelParamGetDlModelParamGetDlModelParamget_dl_model_param.
For further explanations on deep learning models in HALCON,
see the chapter Deep Learning / Model.
Reading in a Model Provided by HALCON
HALCON provides pretrained neural networks for classification and
semantic segmentation. These neural networks are good starting points when
training a custom network. They have been pretrained on a large image dataset.
For anomaly detection, HALCON provides initial models.
- Models for Anomaly Detection
-
The following networks are provided for anomaly detection:
- 'initial_dl_anomaly_medium.hdl'"initial_dl_anomaly_medium.hdl""initial_dl_anomaly_medium.hdl""initial_dl_anomaly_medium.hdl""initial_dl_anomaly_medium.hdl""initial_dl_anomaly_medium.hdl"
-
This neural network is designed to be memory and runtime efficient.
The network expects the images to be of the type 'real'"real""real""real""real""real".
Additionally, it requires certain image properties.
The corresponding values can be retrieved with
get_dl_model_paramget_dl_model_paramGetDlModelParamGetDlModelParamGetDlModelParamget_dl_model_param. Here we list the default values:
'image_width'"image_width""image_width""image_width""image_width""image_width": 480
'image_height'"image_height""image_height""image_height""image_height""image_height": 480
'image_num_channels'"image_num_channels""image_num_channels""image_num_channels""image_num_channels""image_num_channels": 3
'image_range_min'"image_range_min""image_range_min""image_range_min""image_range_min""image_range_min": -2
'image_range_max'"image_range_max""image_range_max""image_range_max""image_range_max""image_range_max": 2
The network architecture allows changes concerning the image dimensions,
but the sizes 'image_width'"image_width""image_width""image_width""image_width""image_width" and 'image_height'"image_height""image_height""image_height""image_height""image_height" have to
be multiples of 32 pixels, resulting in a minimum of 32 pixels.
- 'initial_dl_anomaly_large.hdl'"initial_dl_anomaly_large.hdl""initial_dl_anomaly_large.hdl""initial_dl_anomaly_large.hdl""initial_dl_anomaly_large.hdl""initial_dl_anomaly_large.hdl"
-
This neural network is assumed to be better suited for more complex
anomaly detection tasks.
This comes at the cost of being more time and memory demanding.
The network expects the images to be of the type 'real'"real""real""real""real""real".
Additionally, it requires certain image properties.
The corresponding values can be retrieved with
get_dl_model_paramget_dl_model_paramGetDlModelParamGetDlModelParamGetDlModelParamget_dl_model_param. Here we list the default values:
'image_width'"image_width""image_width""image_width""image_width""image_width": 480
'image_height'"image_height""image_height""image_height""image_height""image_height": 480
'image_num_channels'"image_num_channels""image_num_channels""image_num_channels""image_num_channels""image_num_channels": 3
'image_range_min'"image_range_min""image_range_min""image_range_min""image_range_min""image_range_min": -2
'image_range_max'"image_range_max""image_range_max""image_range_max""image_range_max""image_range_max": 2
The network architecture allows changes concerning the image dimensions,
but the sizes 'image_width'"image_width""image_width""image_width""image_width""image_width" and 'image_height'"image_height""image_height""image_height""image_height""image_height" have to
be multiples of 32 pixels, resulting in a minimum of 32 pixels.
- Models for Global Context Anomaly Detection
-
The following networks are provided for Global Context Anomaly Detection:
- 'pretrained_dl_anomaly_global_context.hdl'"pretrained_dl_anomaly_global_context.hdl""pretrained_dl_anomaly_global_context.hdl""pretrained_dl_anomaly_global_context.hdl""pretrained_dl_anomaly_global_context.hdl""pretrained_dl_anomaly_global_context.hdl"
-
The network expects the images to be of the type 'real'"real""real""real""real""real".
Additionally, it requires certain image properties.
The corresponding values can be retrieved with
get_dl_model_paramget_dl_model_paramGetDlModelParamGetDlModelParamGetDlModelParamget_dl_model_param. Here we list the default values:
'image_width'"image_width""image_width""image_width""image_width""image_width": 256
'image_height'"image_height""image_height""image_height""image_height""image_height": 256
'image_num_channels'"image_num_channels""image_num_channels""image_num_channels""image_num_channels""image_num_channels": 3
'image_range_min'"image_range_min""image_range_min""image_range_min""image_range_min""image_range_min": -127.0
'image_range_max'"image_range_max""image_range_max""image_range_max""image_range_max""image_range_max": 128.0
- Models for Classification
-
The following pretrained neural networks are provided for
classification and usable as backbones for detection:
- 'pretrained_dl_classifier_alexnet.hdl'"pretrained_dl_classifier_alexnet.hdl""pretrained_dl_classifier_alexnet.hdl""pretrained_dl_classifier_alexnet.hdl""pretrained_dl_classifier_alexnet.hdl""pretrained_dl_classifier_alexnet.hdl":
-
This neural network is designed for simple classification tasks.
It is characterized by its convolution kernels in the first
convolution layers, which are larger than those in other networks with
comparable classification performance
(e.g., 'pretrained_dl_classifier_compact.hdl'"pretrained_dl_classifier_compact.hdl""pretrained_dl_classifier_compact.hdl""pretrained_dl_classifier_compact.hdl""pretrained_dl_classifier_compact.hdl""pretrained_dl_classifier_compact.hdl").
This may be beneficial for feature extraction.
This classifier expects the images to be of the type 'real'"real""real""real""real""real".
Additionally, the network is designed for certain image properties.
The corresponding values can be retrieved with
get_dl_model_paramget_dl_model_paramGetDlModelParamGetDlModelParamGetDlModelParamget_dl_model_param. Here we list the default values with
which the classifier has been trained:
'image_width'"image_width""image_width""image_width""image_width""image_width": 224
'image_height'"image_height""image_height""image_height""image_height""image_height": 224
'image_num_channels'"image_num_channels""image_num_channels""image_num_channels""image_num_channels""image_num_channels": 3
'image_range_min'"image_range_min""image_range_min""image_range_min""image_range_min""image_range_min": -127.0
'image_range_max'"image_range_max""image_range_max""image_range_max""image_range_max""image_range_max": 128.0
The network architecture allows changes concerning the image
dimensions. 'image_width'"image_width""image_width""image_width""image_width""image_width" and 'image_height'"image_height""image_height""image_height""image_height""image_height"
should not be less than 29 pixels.
There is no maximum image size, but large image sizes will increase
the memory demand and the runtime significantly.
Changing the image size will reinitialize the weights of the fully
connected layers and therefore makes a retraining necessary.
Note that one can improve the runtime for this network
by fusing the convolution and ReLU layers, see
set_dl_model_paramset_dl_model_paramSetDlModelParamSetDlModelParamSetDlModelParamset_dl_model_param and the parameter
'fuse_conv_relu'"fuse_conv_relu""fuse_conv_relu""fuse_conv_relu""fuse_conv_relu""fuse_conv_relu".
- 'pretrained_dl_classifier_compact.hdl'"pretrained_dl_classifier_compact.hdl""pretrained_dl_classifier_compact.hdl""pretrained_dl_classifier_compact.hdl""pretrained_dl_classifier_compact.hdl""pretrained_dl_classifier_compact.hdl":
-
This neural network is designed to be more memory and runtime
efficient.
The classifier expects the images to be of the type 'real'"real""real""real""real""real".
Additionally, it requires certain image properties.
The corresponding values can be retrieved with
get_dl_model_paramget_dl_model_paramGetDlModelParamGetDlModelParamGetDlModelParamget_dl_model_param. Here we list the default values with
which the classifier has been trained:
'image_width'"image_width""image_width""image_width""image_width""image_width": 224
'image_height'"image_height""image_height""image_height""image_height""image_height": 224
'image_num_channels'"image_num_channels""image_num_channels""image_num_channels""image_num_channels""image_num_channels": 3
'image_range_min'"image_range_min""image_range_min""image_range_min""image_range_min""image_range_min": -127.0
'image_range_max'"image_range_max""image_range_max""image_range_max""image_range_max""image_range_max": 128.0
This network does not contain any fully connected layer.
The network architecture allows changes concerning the image
dimensions. 'image_width'"image_width""image_width""image_width""image_width""image_width" and 'image_height'"image_height""image_height""image_height""image_height""image_height"
should not be less than 15 pixels.
- 'pretrained_dl_classifier_enhanced.hdl'"pretrained_dl_classifier_enhanced.hdl""pretrained_dl_classifier_enhanced.hdl""pretrained_dl_classifier_enhanced.hdl""pretrained_dl_classifier_enhanced.hdl""pretrained_dl_classifier_enhanced.hdl":
-
This neural network has more hidden layers than
'pretrained_dl_classifier_compact.hdl'"pretrained_dl_classifier_compact.hdl""pretrained_dl_classifier_compact.hdl""pretrained_dl_classifier_compact.hdl""pretrained_dl_classifier_compact.hdl""pretrained_dl_classifier_compact.hdl" and is therefore
assumed to be better suited for more complex classification tasks.
This comes at the cost of being more time and memory demanding.
The classifier expects the images to be of the type 'real'"real""real""real""real""real".
Additionally, it requires certain image properties.
The corresponding values can be retrieved with
get_dl_model_paramget_dl_model_paramGetDlModelParamGetDlModelParamGetDlModelParamget_dl_model_param. Here we list the default values with
which the classifier has been trained:
'image_width'"image_width""image_width""image_width""image_width""image_width": 224
'image_height'"image_height""image_height""image_height""image_height""image_height": 224
'image_num_channels'"image_num_channels""image_num_channels""image_num_channels""image_num_channels""image_num_channels": 3
'image_range_min'"image_range_min""image_range_min""image_range_min""image_range_min""image_range_min": -127.0
'image_range_max'"image_range_max""image_range_max""image_range_max""image_range_max""image_range_max": 128.0
The network architecture allows changes concerning the image
dimensions. 'image_width'"image_width""image_width""image_width""image_width""image_width" and 'image_height'"image_height""image_height""image_height""image_height""image_height"
should not be less than 47 pixels.
There is no maximum image size, but large image sizes will increase
the memory demand and the runtime significantly.
Changing the image size will reinitialize the weights of the fully
connected layers and therefore makes a retraining necessary.
- 'pretrained_dl_classifier_mobilenet_v2.hdl'"pretrained_dl_classifier_mobilenet_v2.hdl""pretrained_dl_classifier_mobilenet_v2.hdl""pretrained_dl_classifier_mobilenet_v2.hdl""pretrained_dl_classifier_mobilenet_v2.hdl""pretrained_dl_classifier_mobilenet_v2.hdl":
-
This classifier is a small and low-power model, for what reason it is more
suitable for mobile and embedded vision applications.
The classifier expects the images to be of the type 'real'"real""real""real""real""real".
Additionally, it requires certain image properties.
The corresponding values can be retrieved with
get_dl_model_paramget_dl_model_paramGetDlModelParamGetDlModelParamGetDlModelParamget_dl_model_param. Here we list the default values with
which the classifier has been trained:
'image_width'"image_width""image_width""image_width""image_width""image_width": 224
'image_height'"image_height""image_height""image_height""image_height""image_height": 224
'image_num_channels'"image_num_channels""image_num_channels""image_num_channels""image_num_channels""image_num_channels": 3
'image_range_min'"image_range_min""image_range_min""image_range_min""image_range_min""image_range_min": -127.0
'image_range_max'"image_range_max""image_range_max""image_range_max""image_range_max""image_range_max": 128.0
The network architecture allows changes concerning the image
dimensions. 'image_width'"image_width""image_width""image_width""image_width""image_width" and 'image_height'"image_height""image_height""image_height""image_height""image_height"
should not be less than 32 pixels.
There is no maximum image size, but large image sizes will increase
the memory demand and the runtime significantly.
On the GPU, the network architecture can benefit greatly from special
optimizations, without which the network can be significantly slower.
- 'pretrained_dl_classifier_resnet50.hdl'"pretrained_dl_classifier_resnet50.hdl""pretrained_dl_classifier_resnet50.hdl""pretrained_dl_classifier_resnet50.hdl""pretrained_dl_classifier_resnet50.hdl""pretrained_dl_classifier_resnet50.hdl":
-
As the neural network
'pretrained_dl_classifier_enhanced.hdl'"pretrained_dl_classifier_enhanced.hdl""pretrained_dl_classifier_enhanced.hdl""pretrained_dl_classifier_enhanced.hdl""pretrained_dl_classifier_enhanced.hdl""pretrained_dl_classifier_enhanced.hdl", this classifier is
suited for more complex tasks.
However, due to its special structure, it provides the advantage of making
the training more stable and internally more robust.
The classifier expects the images to be of the type 'real'"real""real""real""real""real".
Additionally, it requires certain image properties.
The corresponding values can be retrieved with
get_dl_model_paramget_dl_model_paramGetDlModelParamGetDlModelParamGetDlModelParamget_dl_model_param. Here we list the default values with
which the classifier has been trained:
'image_width'"image_width""image_width""image_width""image_width""image_width": 224
'image_height'"image_height""image_height""image_height""image_height""image_height": 224
'image_num_channels'"image_num_channels""image_num_channels""image_num_channels""image_num_channels""image_num_channels": 3
'image_range_min'"image_range_min""image_range_min""image_range_min""image_range_min""image_range_min": -127.0
'image_range_max'"image_range_max""image_range_max""image_range_max""image_range_max""image_range_max": 128.0
The network architecture allows changes concerning the image
dimensions. 'image_width'"image_width""image_width""image_width""image_width""image_width" and 'image_height'"image_height""image_height""image_height""image_height""image_height"
should not be less than 32 pixels.
There is no maximum image size, but large image sizes will increase
the memory demand and the runtime significantly.
Despite the fully connected layer a change of the image size does
not lead to a reinitialization of the weights.
- Models for Semantic Segmentation
-
The following pretrained neural networks are provided for semantic
segmentation:
- 'pretrained_dl_edge_extractor.hdl'"pretrained_dl_edge_extractor.hdl""pretrained_dl_edge_extractor.hdl""pretrained_dl_edge_extractor.hdl""pretrained_dl_edge_extractor.hdl""pretrained_dl_edge_extractor.hdl":
-
This neural network is designed and pretrained for edge extraction.
As a consequence this model is meant for two class problems
with one class for edges and one for background.
This network expects the images to be of the type 'real'"real""real""real""real""real".
Additionally, it is designed for certain image properties.
The corresponding values can be retrieved with
get_dl_model_paramget_dl_model_paramGetDlModelParamGetDlModelParamGetDlModelParamget_dl_model_param. Here we list the default values with
which the model has been trained:
'image_width'"image_width""image_width""image_width""image_width""image_width": 512
'image_height'"image_height""image_height""image_height""image_height""image_height": 512
'image_num_channels'"image_num_channels""image_num_channels""image_num_channels""image_num_channels""image_num_channels": 1
'image_range_min'"image_range_min""image_range_min""image_range_min""image_range_min""image_range_min": -127.0
'image_range_max'"image_range_max""image_range_max""image_range_max""image_range_max""image_range_max": 128.0
'num_classes'"num_classes""num_classes""num_classes""num_classes""num_classes": 2
The network architecture allows changes concerning the image dimensions,
but the sizes 'image_width'"image_width""image_width""image_width""image_width""image_width" and 'image_height'"image_height""image_height""image_height""image_height""image_height" have to
be multiples of 16 pixels, resulting in a minimum of 16 pixels.
- 'pretrained_dl_segmentation_compact.hdl'"pretrained_dl_segmentation_compact.hdl""pretrained_dl_segmentation_compact.hdl""pretrained_dl_segmentation_compact.hdl""pretrained_dl_segmentation_compact.hdl""pretrained_dl_segmentation_compact.hdl":
-
This neural network is designed to handle segmentation tasks with
detailed structures and uses only few memory and is runtime efficient.
The network architecture allows changes concerning the image dimensions,
but requires a minimum 'image_width'"image_width""image_width""image_width""image_width""image_width" and
'image_height'"image_height""image_height""image_height""image_height""image_height" of 21 pixels.
- 'pretrained_dl_segmentation_enhanced.hdl'"pretrained_dl_segmentation_enhanced.hdl""pretrained_dl_segmentation_enhanced.hdl""pretrained_dl_segmentation_enhanced.hdl""pretrained_dl_segmentation_enhanced.hdl""pretrained_dl_segmentation_enhanced.hdl":
-
This neural network has more hidden layers than
'pretrained_dl_segmentation_compact.hdl'"pretrained_dl_segmentation_compact.hdl""pretrained_dl_segmentation_compact.hdl""pretrained_dl_segmentation_compact.hdl""pretrained_dl_segmentation_compact.hdl""pretrained_dl_segmentation_compact.hdl" and is therefore
better suited for segmentation tasks including more complex scenes.
The network architecture allows changes concerning the image dimensions,
but requires a minimum 'image_width'"image_width""image_width""image_width""image_width""image_width" and
'image_height'"image_height""image_height""image_height""image_height""image_height" of 47 pixels.
- Models for Deep OCR
-
The following pretrained neural networks are provided for Deep OCR:
- 'pretrained_deep_ocr_recognition.hdl'"pretrained_deep_ocr_recognition.hdl""pretrained_deep_ocr_recognition.hdl""pretrained_deep_ocr_recognition.hdl""pretrained_deep_ocr_recognition.hdl""pretrained_deep_ocr_recognition.hdl":
-
This neural network is the pretrained recognition component of a Deep OCR
model. It is designed to recognize words on images that are cropped to
a single word. This is the recognition component of Deep OCR, which can
be retrained.
This network expects the images to be of the type 'real'"real""real""real""real""real".
Additionally, it is designed for certain image properties. The
corresponding values can be retrieved with get_dl_model_paramget_dl_model_paramGetDlModelParamGetDlModelParamGetDlModelParamget_dl_model_param.
Here we list the default values with which the model has been trained:
'image_width'"image_width""image_width""image_width""image_width""image_width": 120
'image_height'"image_height""image_height""image_height""image_height""image_height": 32
'image_num_channels'"image_num_channels""image_num_channels""image_num_channels""image_num_channels""image_num_channels": 1
'image_range_min'"image_range_min""image_range_min""image_range_min""image_range_min""image_range_min": -1.0
'image_range_max'"image_range_max""image_range_max""image_range_max""image_range_max""image_range_max": 1.0
The network architecture allows changes concerning the image width
'image_width'"image_width""image_width""image_width""image_width""image_width". The image height 'image_height'"image_height""image_height""image_height""image_height""image_height" cannot
be changed. The parameter 'image_width'"image_width""image_width""image_width""image_width""image_width" is very important: its
value can be decreased or increased to adapt to the expected lengths of
words, e.g., due to the average width per character. A bigger
'image_width'"image_width""image_width""image_width""image_width""image_width" will consume more time and memory resources. The
image width 'image_width'"image_width""image_width""image_width""image_width""image_width" may be changed after training.
Reading in a Model in the ONNX Format
You can read in an ONNX model, but there are some points to consider.
- Restrictions
-
Reading in ONNX models with read_dl_modelread_dl_modelReadDlModelReadDlModelReadDlModelread_dl_model, some restrictions
apply:
-
Version 1.8.1 of the ONNX specification is supported. This means only
operators until ONNX operator set version (OpSetVersion) 13 are supported.
For operators with a higher OpSetVersion there is no guarantee that
it can be supported. Further limitations are listed above.
-
Only 32 bit floating point tensors are supported.
-
Only models ending with a SoftMax layer are automatically recognized
as classifiers.
All other models are considered as generic model, thus
models of 'type'"type""type""type""type""type" = 'generic'"generic""generic""generic""generic""generic".
set_dl_model_paramset_dl_model_paramSetDlModelParamSetDlModelParamSetDlModelParamset_dl_model_param can be used to change the model type.
-
The input graph nodes (images) must be of shape dimension 4:
Number of images (='batch_size'"batch_size""batch_size""batch_size""batch_size""batch_size"), 'num_channels'"num_channels""num_channels""num_channels""num_channels""num_channels",
'image_height'"image_height""image_height""image_height""image_height""image_height", and 'image_width'"image_width""image_width""image_width""image_width""image_width".
- Automatic transformations
-
After reading an ONNX model with read_dl_modelread_dl_modelReadDlModelReadDlModelReadDlModelread_dl_model, some network
transformations are executed automatically:
-
Every non-global pooling layer with a resulting
feature map of size 1x1 is converted to a global pooling layer.
Doing so enables resizable input images.
For more information about pooling layer and possible modes of
operation, see the “Solution Guide on Classification”.
-
Layer pairs consisting of a convolution layer without activation
and a directly connected activation layer with ReLU activation are
fused.
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”.
- Supported operations
-
ONNX models with the following operations can be read by
read_dl_modelread_dl_modelReadDlModelReadDlModelReadDlModelread_dl_model:
'Add':
No restrictions.
'ArgMax':-
The following restrictions apply:
-
attribute 'axis'"axis""axis""axis""axis""axis": The value must be 1.
-
attribute 'keepdims'"keepdims""keepdims""keepdims""keepdims""keepdims": The value must be 1.
-
attribute 'select_last_index'"select_last_index""select_last_index""select_last_index""select_last_index""select_last_index": The value
must be 0.
'AveragePool':-
The following restrictions apply:
'BatchNormalization':
No restrictions.
'Clip':-
The following restrictions apply:
'Concat':
No restrictions.
'Constant':-
The following restrictions apply:
-
attribute 'sparse_value'"sparse_value""sparse_value""sparse_value""sparse_value""sparse_value": The attribute is not supported.
-
attribute 'value'"value""value""value""value""value": All entries in the tensor have to be
identical.
-
attribute 'value_floats'"value_floats""value_floats""value_floats""value_floats""value_floats": The attribute is not supported.
-
attribute 'value_ints'"value_ints""value_ints""value_ints""value_ints""value_ints": The attribute is not supported.
-
attribute 'value_string'"value_string""value_string""value_string""value_string""value_string": The attribute is not supported.
-
attribute 'value_strings'"value_strings""value_strings""value_strings""value_strings""value_strings": The attribute is not supported.
'Conv':-
The following restrictions apply:
'Dropout':
No restrictions.
'Gemm':-
The following restrictions apply:
-
attribute 'alpha'"alpha""alpha""alpha""alpha""alpha": The value must be 1.
-
attribute 'beta'"beta""beta""beta""beta""beta": The value must be 1.
-
attribute 'transA'"transA""transA""transA""transA""transA": The value must be
0.
'GlobalAveragePool':
No restrictions.
'GlobalMaxPool':-
The following restrictions apply:
'LeakyRelu':
No restrictions.
'LogSoftmax':-
The following restrictions apply:
'LRN':
No restrictions. Hint: Attribute 'size'"size""size""size""size""size"
has no effect.
'MaxPool':
No restrictions.
'Mean':
No restrictions.
'ReduceMax':-
The following restrictions apply:
'Relu':
No restrictions.
'Resize':-
The following restrictions apply:
-
attribute 'mode'"mode""mode""mode""mode""mode": Only the values 'linear'"linear""linear""linear""linear""linear" or
'bilinear'"bilinear""bilinear""bilinear""bilinear""bilinear" are supported.
-
attribute 'coordinate_transformation_mode'"coordinate_transformation_mode""coordinate_transformation_mode""coordinate_transformation_mode""coordinate_transformation_mode""coordinate_transformation_mode": Only the values
'pytorch_half_pixel'"pytorch_half_pixel""pytorch_half_pixel""pytorch_half_pixel""pytorch_half_pixel""pytorch_half_pixel" and 'align_corners'"align_corners""align_corners""align_corners""align_corners""align_corners" are
supported.
-
input tensor 'roi'"roi""roi""roi""roi""roi": If values are set they have no
effect on the inference.
-
The attributes 'cubic_coeff_a'"cubic_coeff_a""cubic_coeff_a""cubic_coeff_a""cubic_coeff_a""cubic_coeff_a", 'exclude_outside'"exclude_outside""exclude_outside""exclude_outside""exclude_outside""exclude_outside",
'extrapolation_value'"extrapolation_value""extrapolation_value""extrapolation_value""extrapolation_value""extrapolation_value", or 'nearest_mode'"nearest_mode""nearest_mode""nearest_mode""nearest_mode""nearest_mode" have no
effect.
'Reshape':-
The following restrictions apply:
'Sigmoid':
No restrictions.
'Softmax':-
The following restrictions apply:
'Sub':
No restrictions.
'Sum':
No restrictions.
Moreover the ONNX 'metadata_props' field is supported. It is written to
the model parameter 'meta_data'"meta_data""meta_data""meta_data""meta_data""meta_data".
Execution Information
- Multithreading type: reentrant (runs in parallel with non-exclusive operators).
- Multithreading scope: global (may be called from any thread).
- Processed without parallelization.
This operator returns a handle. Note that the state of an instance of this handle type may be changed by specific operators even though the handle is used as an input parameter by those operators.
Parameters
FileNameFileNameFileNameFileNamefileNamefile_name (input_control) filename.read → HTuplestrHTupleHtuple (string) (string) (HString) (char*)
Filename
Default value:
'pretrained_dl_classifier_compact.hdl'
"pretrained_dl_classifier_compact.hdl"
"pretrained_dl_classifier_compact.hdl"
"pretrained_dl_classifier_compact.hdl"
"pretrained_dl_classifier_compact.hdl"
"pretrained_dl_classifier_compact.hdl"
List of values: 'initial_dl_anomaly_large.hdl'"initial_dl_anomaly_large.hdl""initial_dl_anomaly_large.hdl""initial_dl_anomaly_large.hdl""initial_dl_anomaly_large.hdl""initial_dl_anomaly_large.hdl", 'initial_dl_anomaly_medium.hdl'"initial_dl_anomaly_medium.hdl""initial_dl_anomaly_medium.hdl""initial_dl_anomaly_medium.hdl""initial_dl_anomaly_medium.hdl""initial_dl_anomaly_medium.hdl", 'pretrained_deep_ocr_recognition.hdl'"pretrained_deep_ocr_recognition.hdl""pretrained_deep_ocr_recognition.hdl""pretrained_deep_ocr_recognition.hdl""pretrained_deep_ocr_recognition.hdl""pretrained_deep_ocr_recognition.hdl", 'pretrained_dl_anomaly_global_context.hdl'"pretrained_dl_anomaly_global_context.hdl""pretrained_dl_anomaly_global_context.hdl""pretrained_dl_anomaly_global_context.hdl""pretrained_dl_anomaly_global_context.hdl""pretrained_dl_anomaly_global_context.hdl", 'pretrained_dl_classifier_alexnet.hdl'"pretrained_dl_classifier_alexnet.hdl""pretrained_dl_classifier_alexnet.hdl""pretrained_dl_classifier_alexnet.hdl""pretrained_dl_classifier_alexnet.hdl""pretrained_dl_classifier_alexnet.hdl", 'pretrained_dl_classifier_compact.hdl'"pretrained_dl_classifier_compact.hdl""pretrained_dl_classifier_compact.hdl""pretrained_dl_classifier_compact.hdl""pretrained_dl_classifier_compact.hdl""pretrained_dl_classifier_compact.hdl", 'pretrained_dl_classifier_enhanced.hdl'"pretrained_dl_classifier_enhanced.hdl""pretrained_dl_classifier_enhanced.hdl""pretrained_dl_classifier_enhanced.hdl""pretrained_dl_classifier_enhanced.hdl""pretrained_dl_classifier_enhanced.hdl", 'pretrained_dl_classifier_mobilenet_v2.hdl'"pretrained_dl_classifier_mobilenet_v2.hdl""pretrained_dl_classifier_mobilenet_v2.hdl""pretrained_dl_classifier_mobilenet_v2.hdl""pretrained_dl_classifier_mobilenet_v2.hdl""pretrained_dl_classifier_mobilenet_v2.hdl", 'pretrained_dl_classifier_resnet50.hdl'"pretrained_dl_classifier_resnet50.hdl""pretrained_dl_classifier_resnet50.hdl""pretrained_dl_classifier_resnet50.hdl""pretrained_dl_classifier_resnet50.hdl""pretrained_dl_classifier_resnet50.hdl", 'pretrained_dl_edge_extractor.hdl'"pretrained_dl_edge_extractor.hdl""pretrained_dl_edge_extractor.hdl""pretrained_dl_edge_extractor.hdl""pretrained_dl_edge_extractor.hdl""pretrained_dl_edge_extractor.hdl", 'pretrained_dl_segmentation_compact.hdl'"pretrained_dl_segmentation_compact.hdl""pretrained_dl_segmentation_compact.hdl""pretrained_dl_segmentation_compact.hdl""pretrained_dl_segmentation_compact.hdl""pretrained_dl_segmentation_compact.hdl", 'pretrained_dl_segmentation_enhanced.hdl'"pretrained_dl_segmentation_enhanced.hdl""pretrained_dl_segmentation_enhanced.hdl""pretrained_dl_segmentation_enhanced.hdl""pretrained_dl_segmentation_enhanced.hdl""pretrained_dl_segmentation_enhanced.hdl"
File extension: .hdl, .onnx
DLModelHandleDLModelHandleDLModelHandleDLModelHandleDLModelHandledlmodel_handle (output_control) dl_model → HDlModel, HTupleHHandleHTupleHtuple (handle) (IntPtr) (HHandle) (handle)
Handle of the deep learning model.
Result
If the parameters are valid, the operator read_dl_modelread_dl_modelReadDlModelReadDlModelReadDlModelread_dl_model
returns the value 2 (H_MSG_TRUE). If necessary, an exception is raised.
Possible Successors
set_dl_model_paramset_dl_model_paramSetDlModelParamSetDlModelParamSetDlModelParamset_dl_model_param,
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
Alternatives
create_dl_model_detectioncreate_dl_model_detectionCreateDlModelDetectionCreateDlModelDetectionCreateDlModelDetectioncreate_dl_model_detection
References
Open Neural Network Exchange (ONNX), https://onnx.ai/
Module
Deep Learning Inference