get_dl_classifier_train_resultT_get_dl_classifier_train_resultGetDlClassifierTrainResultGetDlClassifierTrainResult (Operator)
Name
get_dl_classifier_train_resultT_get_dl_classifier_train_resultGetDlClassifierTrainResultGetDlClassifierTrainResult — Return the results for the single training step of a deep-learning-based
classifier.
Signature
Description
get_dl_classifier_train_resultget_dl_classifier_train_resultGetDlClassifierTrainResultGetDlClassifierTrainResultGetDlClassifierTrainResult returns the value
GenParamValueGenParamValueGenParamValueGenParamValuegenParamValue of the result GenParamNameGenParamNameGenParamNameGenParamNamegenParamName of a deep
learning training handle DLClassifierTrainResultHandleDLClassifierTrainResultHandleDLClassifierTrainResultHandleDLClassifierTrainResultHandleDLClassifierTrainResultHandle.
The options for GenParamValueGenParamValueGenParamValueGenParamValuegenParamValue are the following:
- 'loss'"loss""loss""loss""loss" or 'total_loss'"total_loss""total_loss""total_loss""total_loss":
-
Current value of the
loss function. See train_dl_classifier_batchtrain_dl_classifier_batchTrainDlClassifierBatchTrainDlClassifierBatchTrainDlClassifierBatch
for a detailed explanation of the loss function.
- 'mll_loss'"mll_loss""mll_loss""mll_loss""mll_loss":
-
Current value of the multinomial logistic
loss function, i.e. 'loss'"loss""loss""loss""loss" without
'regularization_loss'"regularization_loss""regularization_loss""regularization_loss""regularization_loss".
- 'regularization_loss'"regularization_loss""regularization_loss""regularization_loss""regularization_loss":
Current value of the regularization
loss function, i.e. 'loss'"loss""loss""loss""loss" without
'mll_loss'"mll_loss""mll_loss""mll_loss""mll_loss".
For an explanation of the concept of deep-learning-based classification
see the introduction of chapter Deep Learning / Classification.
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
DLClassifierTrainResultHandleDLClassifierTrainResultHandleDLClassifierTrainResultHandleDLClassifierTrainResultHandleDLClassifierTrainResultHandle (input_control) dl_classifier_train_result → HDlClassifierTrainResult, HTupleHTupleHtuple (handle) (IntPtr) (HHandle) (handle)
Handle of the training results from the
deep-learning-based classifier.
GenParamNameGenParamNameGenParamNameGenParamNamegenParamName (input_control) attribute.name(-array) → HTupleHTupleHtuple (string) (string) (HString) (char*)
Name of the generic parameter.
Default value:
'loss'
"loss"
"loss"
"loss"
"loss"
List of values: 'loss'"loss""loss""loss""loss", 'mll_loss'"mll_loss""mll_loss""mll_loss""mll_loss", 'regularization_loss'"regularization_loss""regularization_loss""regularization_loss""regularization_loss", 'total_loss'"total_loss""total_loss""total_loss""total_loss"
GenParamValueGenParamValueGenParamValueGenParamValuegenParamValue (output_control) attribute.name(-array) → HTupleHTupleHtuple (real / integer / string) (double / int / long / string) (double / Hlong / HString) (double / Hlong / char*)
Value of the generic parameter.
Result
If the parameters are valid, the operator
get_dl_classifier_train_resultget_dl_classifier_train_resultGetDlClassifierTrainResultGetDlClassifierTrainResultGetDlClassifierTrainResult returns the value 2 (H_MSG_TRUE). If
necessary, an exception is raised.
Possible Predecessors
train_dl_classifier_batchtrain_dl_classifier_batchTrainDlClassifierBatchTrainDlClassifierBatchTrainDlClassifierBatch
Possible Successors
clear_dl_classifier_train_resultclear_dl_classifier_train_resultClearDlClassifierTrainResultClearDlClassifierTrainResultClearDlClassifierTrainResult
Module
Deep Learning Training