create_dl_layer_activationT_create_dl_layer_activationCreateDlLayerActivationCreateDlLayerActivationcreate_dl_layer_activation (Operator)

Name

create_dl_layer_activationT_create_dl_layer_activationCreateDlLayerActivationCreateDlLayerActivationcreate_dl_layer_activation — Create an activation layer.

Signature

Description

The operator create_dl_layer_activationcreate_dl_layer_activationCreateDlLayerActivationCreateDlLayerActivationCreateDlLayerActivationcreate_dl_layer_activation creates an activation layer whose handle is returned in DLLayerActivationDLLayerActivationDLLayerActivationDLLayerActivationDLLayerActivationdllayer_activation.

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

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

The parameter ActivationTypeActivationTypeActivationTypeActivationTypeactivationTypeactivation_type sets the type of the activation. Supported activation types are:

'relu'"relu""relu""relu""relu""relu":

Rectified linear unit (ReLU) activation. By setting a specific ReLU parameter, another type can be specified instead of the standard ReLU:

• Standard ReLU, defined as follows:

• Bounded ReLU, defined as follows: Setting the generic parameter 'upper_bound'"upper_bound""upper_bound""upper_bound""upper_bound""upper_bound" will result in a bounded ReLU and determines the value of .

• Leaky ReLU:, defined as follows: Setting the generic parameter 'leaky_relu_alpha'"leaky_relu_alpha""leaky_relu_alpha""leaky_relu_alpha""leaky_relu_alpha""leaky_relu_alpha" results in a leaky ReLU and determines the value .

'sigmoid'"sigmoid""sigmoid""sigmoid""sigmoid""sigmoid":

Sigmoid activation, which is defined as follows.

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"

'upper_bound'"upper_bound""upper_bound""upper_bound""upper_bound""upper_bound":

Float value defining an upper bound for a rectified linear unit. If the activation layer is part of a model which has been created using create_dl_modelcreate_dl_modelCreateDlModelCreateDlModelCreateDlModelcreate_dl_model, the upper bound can be unset. To do so, use set_dl_model_layer_paramset_dl_model_layer_paramSetDlModelLayerParamSetDlModelLayerParamSetDlModelLayerParamset_dl_model_layer_param and set an empty tuple for 'upper_bound'"upper_bound""upper_bound""upper_bound""upper_bound""upper_bound".

Default: []

'leaky_relu_alpha'"leaky_relu_alpha""leaky_relu_alpha""leaky_relu_alpha""leaky_relu_alpha""leaky_relu_alpha":

Float value defining the alpha parameter of a leaky ReLU.

Restriction: The value of 'leaky_relu_alpha'"leaky_relu_alpha""leaky_relu_alpha""leaky_relu_alpha""leaky_relu_alpha""leaky_relu_alpha" must be positive or zero.

Default: 0.0

Certain parameters of layers created using this operator create_dl_layer_activationcreate_dl_layer_activationCreateDlLayerActivationCreateDlLayerActivationCreateDlLayerActivationcreate_dl_layer_activation 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