train_dl_model_anomaly_dataset — Train a deep learning model for anomaly detection.
train_dl_model_anomaly_dataset performs the training
of a deep learning model with 'type'='anomaly_detection'
This operator processes the full training dataset at once.
This is in contrast to the operator
The iterations over the dataset are performed internally by the operator.
Consequently, you only need to call this operator once with the full training
dataset to train your anomaly detection model.
The training dataset is handed over in the tuple of dictionaries
See the chapter Deep Learning / Model for further information to the
used dictionaries and their keys.
The operator expects within the training dataset only images without anomaly
to train the anomaly detection model.
DLTrainParam can be used to change the
The following values are supported:
This parameter specifies the maximum number of epochs performed
In case the criterion specified by
error_threshold is reached in
an earlier epoch, the training will terminate regardless.
max_num_epochs = 30.
This parameter is a termination criterion for the training.
If the training error is less than the specified
error_threshold, the training terminates successfully.
error_threshold <= 1.0.
error_threshold = 0.001.
This parameter determines the percentage of information of each image used
Since images tend to contain an abundance of information,
it is advisable to reduce its amount.
domain_ratio can decrease the time needed
Please note, however, sufficient information needs to remain and
therefore this value should not be set too small either.
Otherwise the training result might not be satisfactory or the training
itself might even fail.
Restriction: 0.0 <
domain_ratio <= 1.0.
domain_ratio = 0.1.
This parameter can be set to regularize the training in order to
regularization_noise = 0.0.
The output dictionary
DLTrainResult contains the following values:
The best error received during training.
The epoch in which the error
final_error was achieved.
To run this operator on GPU by setting 'runtime' to
set_dl_model_param), cuDNN and cuBLAS are required.
For further details, please refer to the
paragraph “Requirements for Deep Learning”. Alternatively, this operator
can also be run on CPU by setting 'runtime' to 'cpu'.
Deep learning model handle.
Tuple of Dictionaries with input images and corresponding information.
Parameter for training the anomaly detection model.
Default value: 
Dictionary with the train result data.
If the parameters are valid, the operator
returns the value 2 (H_MSG_TRUE). If necessary, an exception is raised.
Deep Learning Training