Forum
Login
Register

Welcome to our Support Center
UpdatedOctober 29, 2025

MaxPool

Description

MaxPool consumes an input tensor X and applies max pooling across the tensor according to kernel sizes, stride sizes, and pad lengths. max pooling consisting of computing the max on all values of a subset of the input tensor according to the kernel size and downsampling the data into the output tensor Y for further processing.

 

 

The output spatial shape is calculated differently depending on whether explicit padding is used, where pads is employed, or auto padding is used, where auto_pad is utilized. With explicit padding (https://pytorch.org/docs/stable/generated/torch.nn.MaxPool2d.html?highlight=maxpool#torch.nn.MaxPool2d):

output_spatial_shape[i] = floor((input_spatial_shape[i] + pad_shape[i] - dilation[i] * (kernel_shape[i] - 1) - 1) / strides_spatial_shape[i] + 1)

 

or

output_spatial_shape[i] = ceil((input_spatial_shape[i] + pad_shape[i] - dilation[i] * (kernel_shape[i] - 1) - 1) / strides_spatial_shape[i] + 1)

 

if ceil_mode is enabled.Β pad_shapeΒ is the sum of pads along axisΒ i.

auto_padΒ is a DEPRECATED attribute. If you are using them currently, the output spatial shape will be following when ceil_mode is enabled:

VALID: output_spatial_shape[i] = ceil((input_spatial_shape[i] - ((kernel_spatial_shape[i] - 1) * dilations[i] + 1) + 1) / strides_spatial_shape[i])
SAME_UPPER or SAME_LOWER: output_spatial_shape[i] = ceil(input_spatial_shape[i] / strides_spatial_shape[i])

 

or when ceil_mode is disabled (https://www.tensorflow.org/api_docs/python/tf/keras/layers/AveragePooling2D):

VALID: output_spatial_shape[i] = floor((input_spatial_shape[i] - ((kernel_spatial_shape[i] - 1) * dilations[i] + 1)) / strides_spatial_shape[i]) + 1
SAME_UPPER or SAME_LOWER: output_spatial_shape[i] = floor((input_spatial_shape[i] - 1) / strides_spatial_shape[i]) + 1

 

And pad shape will be following ifΒ SAME_UPPERΒ orΒ SAME_LOWER:

pad_shape[i] = (output_spatial_shape[i] - 1) * strides_spatial_shape[i] + ((kernel_spatial_shape[i] - 1) * dilations[i] + 1) - input_spatial_shape[i]

 

The output of each pooling window is maximum number of elements exclude pad.

 

Input parameters

 

specified_outputs_name :Β array, this parameter lets you manually assign custom names to the output tensors of a node.
X (heterogeneous) – T : object, input data tensor from the previous operator; dimensions for image case are (N x C x H x W), where N is the batch size, C is the number of channels, and H and W are the height and the width of the data. For non image case, the dimensions are in the form of (N x C x D1 x D2 … Dn), where N is the batch size. Optionally, if dimension denotation is in effect, the operation expects the input data tensor to arrive with the dimension denotation of [DATA_BATCH, DATA_CHANNEL, DATA_FEATURE, DATA_FEATURE …].

Β Parameters :Β cluster,

Β auto_padΒ :Β enum,Β auto_pad must be either NOTSET, SAME_UPPER, SAME_LOWER or VALID. Where default value is NOTSET, which means explicit padding is used. SAME_UPPER or SAME_LOWER mean pad the input so thatΒ output_shapeΒ =Β ceil(input_shapeΒ /Β strides)Β for each axisΒ i. The padding is split between the two sides equally or almost equally (depending on whether it is even or odd). In case the padding is an odd number, the extra padding is added at the end for SAME_UPPER and at the beginning for SAME_LOWER.
Default value β€œNOTSET”.
Β ceil_modeΒ :Β boolean, whether to use ceil or floor (default) to compute the output shape.
Default value β€œFalse”.
Β dilations :Β array,Β dilation value along each spatial axis of filter. If not present, the dilation defaults to 1 along each spatial axis.
Default value β€œempty”.
Β kernel_shapeΒ :Β array,Β the size of the kernel along each axis.
Default value β€œempty”.
Β padsΒ :Β array,Β padding for the beginning and ending along each spatial axis, it can take any value greater than or equal to 0. The value represent the number of pixels added to the beginning and end part of the corresponding axis.Β padsΒ format should be as follow [x1_begin, x2_begin…x1_end, x2_end,…], where xi_begin the number of pixels added at the beginning of axisΒ iΒ and xi_end, the number of pixels added at the end of axisΒ i. This attribute cannot be used simultaneously with auto_pad attribute. If not present, the padding defaults to 0 along start and end of each spatial axis.
Default value β€œempty”.
storage_orderΒ :Β enum, the storage order of the tensor. 0 is row major, and 1 is column major. This attribute is used only to convert an n-tuple index value into a single integer value for producing the second output.
Default value β€œrow major”.
Β stridesΒ :Β array,Β stride along each spatial axis. If not present, the stride defaults to 1 along each spatial axis.
Default value β€œempty”.
Β training?Β :Β boolean, whether the layer is in training mode (can store data for backward).
Default value β€œTrue”.
Β lda coeff :Β float, defines the coefficient by which the loss derivative will be multiplied before being sent to the previous layer (since during the backward run we go backwards).
Default value β€œ1”.

Β name (optional) :Β string,Β name of the node.

Output parameters

Β Graphs out :Β cluster, ONNX model architecture.

Y (heterogeneous) – T : object, output data tensor from average or max pooling across the input tensor. Dimensions will vary based on various kernel, stride, and pad sizes. Floor value of the dimension is used
Indices (optional, heterogeneous) – I : object, indices tensor from max pooling across the input tensor. The dimensions of indices are the same as output tensor. The values in indices of are the indices of the selected values during pooling. The indices are computed as flatten 1-D tensor, and the indices do not consider padding. So the values in indices are in [0, N x C x D1 x … x Dn).

Type Constraints

T in (tensor(double),Β tensor(float),Β tensor(float16),Β tensor(int8),Β tensor(uint8)) : Constrain input and output types to float and 8 bit tensors.

I in (tensor(int64)) : Constrain index tensor to int64

Example

All these exemples are snippets PNG, you can drop these Snippet onto the block diagram and get the depicted code added to your VI (Do not forget to install Deep Learning library to run it).
Table of Contents