create_dl_layer_poolingT_create_dl_layer_poolingCreateDlLayerPoolingCreateDlLayerPoolingcreate_dl_layer_pooling (Operator)

Name

create_dl_layer_poolingT_create_dl_layer_poolingCreateDlLayerPoolingCreateDlLayerPoolingcreate_dl_layer_pooling — Create a pooling layer.

Signature

Description

The operator create_dl_layer_poolingcreate_dl_layer_poolingCreateDlLayerPoolingCreateDlLayerPoolingCreateDlLayerPoolingcreate_dl_layer_pooling creates a pooling layer whose handle is returned in DLLayerPoolingDLLayerPoolingDLLayerPoolingDLLayerPoolingDLLayerPoolingdllayer_pooling.

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 KernelSizeKernelSizeKernelSizeKernelSizekernelSizekernel_size specifies the filter kernel in the dimensions width and height.

The parameter StrideStrideStrideStridestridestride specifies how the filter is shifted.

The values for KernelSizeKernelSizeKernelSizeKernelSizekernelSizekernel_size and StrideStrideStrideStridestridestride can be set as

• a single value which is used for both dimensions

• a tuple [width, height] and [column, row], respectively.

The parameter PaddingPaddingPaddingPaddingpaddingpadding determines the padding, thus how many pixels with value 0 are appended on the boarder of the processed input image. Supported values are:

• 'half_kernel_size'"half_kernel_size""half_kernel_size""half_kernel_size""half_kernel_size""half_kernel_size": The number of appended pixels depends on the specifies KernelSizeKernelSizeKernelSizeKernelSizekernelSizekernel_size. More precisely they are calculated as , where for the padding on the left / right bound the value of KernelSizeKernelSizeKernelSizeKernelSizekernelSizekernel_size in dimension width is regarded and for the padding on the upper / lower bound the value of KernelSizeKernelSizeKernelSizeKernelSizekernelSizekernel_size in height.

• 'implicit'"implicit""implicit""implicit""implicit""implicit": No pixels are appended on the left or on the top of the input image. The number of pixels appended on the right or lower bound of the input image is , or zero if the kernel size is a divisor of the input dimension. stands for the input width or height.

• 'none'"none""none""none""none""none": No pixels are appended.

• Number of pixels: Specify the number of pixels appended on each border. To do so, the following tuple lengths are supported:

  • Single number: Padding in all four directions left/right/top/bottom.

  • Two numbers: Padding in left/right and top/bottom: [l/r, t/b].

  • Four numbers: Padding on left, right, top, bottom side: [l,r,t,b].

    Restriction: 'runtime'"runtime""runtime""runtime""runtime""runtime" 'gpu'"gpu""gpu""gpu""gpu""gpu" does not support asymmetric padding, i.e., the padding values for the left and right side must be equal, as well as the padding values for the top and bottom side.

  Restriction: The integer padding values must be smaller than the value set for KernelSizeKernelSizeKernelSizeKernelSizekernelSizekernel_size in the corresponding dimension.

The output dimensions of the pooling layer are given by Thereby we use the following values: : output width, : input width, : number of pixels added to the left/top of the input image, and : number of pixels added to the right/bottom of the input image.

The parameter ModeModeModeModemodemode specifies the mode of the pooling operation. Supported modes are:

'average'"average""average""average""average""average":

The resulting pixel value is the average of all pixel values in the filter.

'maximum'"maximum""maximum""maximum""maximum""maximum":

The resulting pixel value is the maximum of all pixel values in the filter.

'global_average'"global_average""global_average""global_average""global_average""global_average":

Same as mode 'average'"average""average""average""average""average", but the internally used kernel size is changed to and the internally used stride is set to the new kernel size. Following the above formula, this can be used to control the desired output dimensions without the knowledge of the dimensions of the input dimensions. E.g., if the average over all pixel values of the input shall be returned, set the KernelSizeKernelSizeKernelSizeKernelSizekernelSizekernel_size to 1 and the output width and height is equal to 1. As a consequence, the output dimension equals KernelSizeKernelSizeKernelSizeKernelSizekernelSizekernel_size if KernelSizeKernelSizeKernelSizeKernelSizekernelSizekernel_size is a divisor of the input dimension.

'global_maximum'"global_maximum""global_maximum""global_maximum""global_maximum""global_maximum":

Same as mode 'global_average'"global_average""global_average""global_average""global_average""global_average", but the maximum is calculated instead of the average.

For more information about the pooling layer see the “Solution Guide on Classification”.

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_poolingcreate_dl_layer_poolingCreateDlLayerPoolingCreateDlLayerPoolingCreateDlLayerPoolingcreate_dl_layer_pooling 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