create_dl_layer_depth_maxT_create_dl_layer_depth_maxCreateDlLayerDepthMaxCreateDlLayerDepthMaxcreate_dl_layer_depth_max (Operator)

Name

create_dl_layer_depth_maxT_create_dl_layer_depth_maxCreateDlLayerDepthMaxCreateDlLayerDepthMaxcreate_dl_layer_depth_max — Create a depth max layer.

Signature

Description

The operator create_dl_layer_depth_maxcreate_dl_layer_depth_maxCreateDlLayerDepthMaxCreateDlLayerDepthMaxCreateDlLayerDepthMaxcreate_dl_layer_depth_max creates a depth max layer.

The parameter DLLayerInputDLLayerInputDLLayerInputDLLayerInputDLLayerInputdllayer_input determines the feeding input layer and expects the layer handle as value.

There are two possible output layers:

• DLLayerDepthMaxArgDLLayerDepthMaxArgDLLayerDepthMaxArgDLLayerDepthMaxArgDLLayerDepthMaxArgdllayer_depth_max_arg: Handle to a depth max layer with mode 'argmax'"argmax""argmax""argmax""argmax""argmax".

• DLLayerDepthMaxValueDLLayerDepthMaxValueDLLayerDepthMaxValueDLLayerDepthMaxValueDLLayerDepthMaxValuedllayer_depth_max_value: Handle to a depth max layer with mode 'value'"value""value""value""value""value".

If they are returned depends on the mode DepthMaxModeDepthMaxModeDepthMaxModeDepthMaxModedepthMaxModedepth_max_mode. Note, these parameters only need to be set in case such an output layer is requested (see DepthMaxModeDepthMaxModeDepthMaxModeDepthMaxModedepthMaxModedepth_max_mode).

The parameter LayerNameLayerNameLayerNameLayerNamelayerNamelayer_name defines the name of the output layer(s) depending on DepthMaxModeDepthMaxModeDepthMaxModeDepthMaxModedepthMaxModedepth_max_mode:

• 'argmax'"argmax""argmax""argmax""argmax""argmax": name of DLLayerDepthMaxArgDLLayerDepthMaxArgDLLayerDepthMaxArgDLLayerDepthMaxArgDLLayerDepthMaxArgdllayer_depth_max_arg.

• 'value'"value""value""value""value""value": name of DLLayerDepthMaxValueDLLayerDepthMaxValueDLLayerDepthMaxValueDLLayerDepthMaxValueDLLayerDepthMaxValuedllayer_depth_max_value.

• 'argmax_and_value'"argmax_and_value""argmax_and_value""argmax_and_value""argmax_and_value""argmax_and_value": name of DLLayerDepthMaxArgDLLayerDepthMaxArgDLLayerDepthMaxArgDLLayerDepthMaxArgDLLayerDepthMaxArgdllayer_depth_max_arg, while the layer DLLayerDepthMaxValueDLLayerDepthMaxValueDLLayerDepthMaxValueDLLayerDepthMaxValueDLLayerDepthMaxValuedllayer_depth_max_value receives the same name with the suffix string '_value'"_value""_value""_value""_value""_value" appended to it.

Note that if creating a model using create_dl_modelcreate_dl_modelCreateDlModelCreateDlModelCreateDlModelcreate_dl_model each layer of the created network must have an unique name.

The mode DepthMaxModeDepthMaxModeDepthMaxModeDepthMaxModedepthMaxModedepth_max_mode indicates which depth max value is actually returned as output. The following values are supported:

'argmax'"argmax""argmax""argmax""argmax""argmax":

The depth index of the maximal value is returned in DLLayerDepthMaxArgDLLayerDepthMaxArgDLLayerDepthMaxArgDLLayerDepthMaxArgDLLayerDepthMaxArgdllayer_depth_max_arg.

'value'"value""value""value""value""value":

The maximal value itself is returned in DLLayerDepthMaxValueDLLayerDepthMaxValueDLLayerDepthMaxValueDLLayerDepthMaxValueDLLayerDepthMaxValuedllayer_depth_max_value.

'argmax_and_value'"argmax_and_value""argmax_and_value""argmax_and_value""argmax_and_value""argmax_and_value":

Both are returned, the depth index of the maximal value in DLLayerDepthMaxArgDLLayerDepthMaxArgDLLayerDepthMaxArgDLLayerDepthMaxArgDLLayerDepthMaxArgdllayer_depth_max_arg, and the maximal value itself in the output layer DLLayerDepthMaxValueDLLayerDepthMaxValueDLLayerDepthMaxValueDLLayerDepthMaxValueDLLayerDepthMaxValuedllayer_depth_max_value.

The following generic parameters GenParamNameGenParamNameGenParamNameGenParamNamegenParamNamegen_param_name and the corresponding values GenParamValueGenParamValueGenParamValueGenParamValuegenParamValuegen_param_value are supported:

'is_inference_output'"is_inference_output""is_inference_output""is_inference_output""is_inference_output""is_inference_output":

Determines whether apply_dl_modelapply_dl_modelApplyDlModelApplyDlModelApplyDlModelapply_dl_model will include the output of this layer in the dictionary DLResultBatchDLResultBatchDLResultBatchDLResultBatchDLResultBatchdlresult_batch even without specifying this layer in OutputsOutputsOutputsOutputsoutputsoutputs ('true'"true""true""true""true""true") or not ('false'"false""false""false""false""false").

Default: 'false'"false""false""false""false""false"

'num_trainable_params'"num_trainable_params""num_trainable_params""num_trainable_params""num_trainable_params""num_trainable_params":

Number of trainable parameters (weights and biases) of the layer.

Certain parameters of layers created using this operator create_dl_layer_depth_maxcreate_dl_layer_depth_maxCreateDlLayerDepthMaxCreateDlLayerDepthMaxCreateDlLayerDepthMaxcreate_dl_layer_depth_max can be set and retrieved using further operators. The following tables give an overview, which parameters can be set using set_dl_model_layer_paramset_dl_model_layer_paramSetDlModelLayerParamSetDlModelLayerParamSetDlModelLayerParamset_dl_model_layer_param and which ones can be retrieved using get_dl_model_layer_paramget_dl_model_layer_paramGetDlModelLayerParamGetDlModelLayerParamGetDlModelLayerParamget_dl_model_layer_param or get_dl_layer_paramget_dl_layer_paramGetDlLayerParamGetDlLayerParamGetDlLayerParamget_dl_layer_param. Note, the operators set_dl_model_layer_paramset_dl_model_layer_paramSetDlModelLayerParamSetDlModelLayerParamSetDlModelLayerParamset_dl_model_layer_param and get_dl_model_layer_paramget_dl_model_layer_paramGetDlModelLayerParamGetDlModelLayerParamGetDlModelLayerParamget_dl_model_layer_param require a model created by create_dl_modelcreate_dl_modelCreateDlModelCreateDlModelCreateDlModelcreate_dl_model.

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

Module

Deep Learning Training