create_dl_layer_depth_max🔗
Short description🔗
create_dl_layer_depth_max — Create a depth max layer.
Signature🔗
create_dl_layer_depth_max( dl_layer DLLayerInput, string LayerName, string DepthMaxMode, attribute.name GenParamName, attribute.value GenParamValue, out dl_layer DLLayerDepthMaxArg, out dl_layer DLLayerDepthMaxValue )
Description🔗
The operator create_dl_layer_depth_max creates a depth max layer.
The parameter DLLayerInput determines the feeding input layer and
expects the layer handle as value.
There are two possible output layers depending on DepthMaxMode:
-
DLLayerDepthMaxArg: Handle to a depth max layer with mode 'argmax'. -
DLLayerDepthMaxValue: Handle to a depth max layer with mode 'value'.
Note, these parameters only need to be set in case such an output layer
is requested (see DepthMaxMode).
The parameter LayerName defines the name of the output layer(s)
depending on DepthMaxMode:
-
'argmax': name of
DLLayerDepthMaxArg. -
'value': name of
DLLayerDepthMaxValue. -
'argmax_and_value': name of
DLLayerDepthMaxArg, while the layerDLLayerDepthMaxValuereceives the same name with the suffix string '_value' appended to it.
Note that if creating a model using create_dl_model each layer of the
created network must have a unique name.
The mode DepthMaxMode indicates which depth max value is
actually returned as output.
The following values are supported:
-
'argmax': The
depthindex of the maximal value is returned inDLLayerDepthMaxArg. -
'value': The maximal value itself is returned in
DLLayerDepthMaxValue. -
'argmax_and_value': Both are returned, the
depthindex of the maximal value in the output layerDLLayerDepthMaxArg, and the maximal value itself in the output layerDLLayerDepthMaxValue.
The following generic parameters GenParamName and the corresponding
values GenParamValue are supported:
-
'is_inference_output': Determines whether
apply_dl_modelwill include the output of this layer in the dictionaryDLResultBatcheven without specifying this layer inOutputs('true') or not ('false').Default: 'false'
Certain parameters of layers created using this operator
create_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_param and which ones can be retrieved
using get_dl_model_layer_param or get_dl_layer_param. Note, the
operators set_dl_model_layer_param and get_dl_model_layer_param
require a model created by create_dl_model.
| Layer Parameters | set |
get |
|---|---|---|
'input_layer' (DLLayerInput) |
x |
|
'mode' (DepthMaxMode) |
x |
x |
'name' (LayerName) |
x |
x |
'output_layer' (DLLayerDepthMaxArg and/or DLLayerDepthMaxValue) |
x |
|
| 'shape' | x |
|
| 'type' | x |
| Generic Layer Parameters | set |
get |
|---|---|---|
| 'is_inference_output' | x |
|
| 'num_trainable_params' | x |
Execution information🔗
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🔗
DLLayerInput (input_control) dl_layer → (handle)
Feeding layer.
LayerName (input_control) string → (string)
Name of the output layer.
DepthMaxMode (input_control) string → (string)
Mode to indicate type of return value.
Default: 'argmax'
List of values: 'argmax', 'argmax_and_value', 'value'
GenParamName (input_control) attribute.name(-array) → (string)
Generic input parameter names.
Default: []
List of values: 'is_inference_output'
GenParamValue (input_control) attribute.value(-array) → (string / integer / real)
Generic input parameter values.
Default: []
Suggested values: 'true', 'false'
DLLayerDepthMaxArg (output_control) dl_layer(-array) → (handle)
Optional, depth max layer with mode 'argmax'.
DLLayerDepthMaxValue (output_control) dl_layer(-array) → (handle)
Optional, depth max layer with mode 'value'.
Module🔗
Deep Learning Professional