create_dl_layer_elementwiseT_create_dl_layer_elementwiseCreateDlLayerElementwiseCreateDlLayerElementwisecreate_dl_layer_elementwise (Operator)

Name

create_dl_layer_elementwiseT_create_dl_layer_elementwiseCreateDlLayerElementwiseCreateDlLayerElementwisecreate_dl_layer_elementwise — Create an elementwise layer.

Signature

Description

The operator create_dl_layer_elementwisecreate_dl_layer_elementwiseCreateDlLayerElementwiseCreateDlLayerElementwiseCreateDlLayerElementwisecreate_dl_layer_elementwise creates an element-wise layer whose handle is returned in DLLayerElementWiseDLLayerElementWiseDLLayerElementWiseDLLayerElementWiseDLLayerElementWisedllayer_element_wise.

An elementwise layer applies a certain operation to every data tensor of the input layers handles and to each element of the data tensor. As a consequence, all input data tensors should be of the same shape and the output tensor has the same shape as the first input tensor.

Depending on OperationOperationOperationOperationoperationoperation, the layer supports implicit broadcasting. I.e., if one of the shape dimensions (batch_size, depth, height, width) of the second or any of the following inputs is 1, the values are implicitly duplicated along that dimension to match the shape of the first input. See also the restrictions below.

The parameter DLLayerInputsDLLayerInputsDLLayerInputsDLLayerInputsDLLayerInputsdllayer_inputs determines the feeding input layers.

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 an unique name.

The parameter OperationOperationOperationOperationoperationoperation specifies the operation that is applied. The supported operations are:

• 'maximum'"maximum""maximum""maximum""maximum""maximum": Element-wise maximum. Broadcasting is fully supported for this operation.

• 'minimum'"minimum""minimum""minimum""minimum""minimum": Element-wise minimum. Broadcasting is fully supported for this operation.

• 'product'"product""product""product""product""product": Element-wise product. Broadcasting is supported for this operation, but all inputs following the second input must have the same shape as the second input.

• 'sum'"sum""sum""sum""sum""sum": Element-wise summation. Broadcasting is not supported for this operation.

The optional parameter CoefficientsCoefficientsCoefficientsCoefficientscoefficientscoefficients determines a weighting coefficient for every input tensor. The number of values in CoefficientsCoefficientsCoefficientsCoefficientscoefficientscoefficients must match the number of feeding layers in DLLayerInputsDLLayerInputsDLLayerInputsDLLayerInputsDLLayerInputsdllayer_inputs. Set CoefficientsCoefficientsCoefficientsCoefficientscoefficientscoefficients equal to [] if no coefficients shall be used in the element-wise operation.

Restriction: No coefficients can be set for OperationOperationOperationOperationoperationoperation = 'product'"product""product""product""product""product".

Example: for OperationOperationOperationOperationoperationoperation = 'sum'"sum""sum""sum""sum""sum", the -th element of the output data tensor is given by where is the number of input data tensors.

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_elementwisecreate_dl_layer_elementwiseCreateDlLayerElementwiseCreateDlLayerElementwiseCreateDlLayerElementwisecreate_dl_layer_elementwise 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