Welcome to our Support Center

MaxPool3D

Description

Setup and add the max pooling 3D layer into the model during the definition graph step. Type : polymorphic.

 

Input parameters

 

Graph in : model architecture.

 parameters : layer parameters.

 size : integer array, factors by which to downscale (dim1, dim2, dim3). (2, 2, 2) will halve the size of the 3D input in each dimension.
Default value “[2,2,2]”.
 stride : integer array, strides values.
Default value “[0,0,0]”.
 padding : boolean, “valid“or “same“. “valid” means no padding. “same” results in padding evenly to the left/right or up/down of the input such that output has the same height/width dimension as the input.
Default value “False”.
 data_format : enum, one of channels_last or channels_first (default) . The ordering of the dimensions in the inputs. channels_last corresponds to inputs with shape (batch, height, width, channels) while channels_first corresponds to inputs with shape (batch, channels, height, width).
Default value “channels_first”.
 training? : boolean, whether the layer is in training mode (can store data for backward).
Default value “True”.
 lda_coeff : 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 “1”.

 in/out param :

 input_shape : integer array, shape (not including the batch axis). NB : To be used only if it is the first layer of the model.
 output_behavior : enum, setup if the layer is an output layer.
Default “Not Output”​​.

name (optional) : string, name of the layer.

 

Output parameters

 

Graph out : model architecture.

Dimension

Input shape

5D tensor with shape :

  • If data_format = ‘channels_last’ : (batch_size, spatial_dim1, spatial_dim2, spatial_dim3, channels).
  • If data_format = ‘channels_first’ : (batch_size, channels, spatial_dim1, spatial_dim2, spatial_dim3).

Output shape

5D tensor with shape :

  • If data_format = ‘channels_last’ : (batch_size, pooled_dim1, pooled_dim2, pooled_dim3, channels).
  • If data_format = ‘channels_first’ : (batch_size, channels, pooled_dim1, pooled_dim2, pooled_dim3).

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 HAIBAL library to run it).

MaxPool3D layer with explicit input layer

1 – Generate a set of data

We generate an array of data of type single and shape [batch_size = 10, channels = 7, spatial_dim1 = 5, spatial_dim2 = 5, spatial_dim3 = 3].

2 – Define graph

First, we define the first layer of the graph which is an Input layer (explicit input layer method). This layer is setup as an input array shaped [channels = 7, spatial_dim1 = 5, spatial_dim2 = 5, spatial_dim3 = 3].
Then we add to the graph the MaxPool3D layer.

3 – Run graph

We call the forward method and retrieve the result with the “Prediction 5D” method.
This method returns two variables, the first one is the layer information (cluster composed of the layer name, the graph index and the shape of the output layer) and the second one is the prediction with a shape of [batch_size, channels, spatial_dim1, spatial_dim2, spatial_dim3].

 

MaxPool3D layer with implicit input layer

1 – Generate a set of data

We generate an array of data of type single and shape [batch_size = 10, channels = 7, spatial_dim1 = 5, spatial_dim2 = 5, spatial_dim3 = 3].

2 – Define graph

First, we define the MaxPool3D layer as the input layer of the graph (implicit input layer method). To do this, we send in the “input_shape” variable of the “in/out param” cluster an array of shape [channels = 7, spatial_dim1 = 5, spatial_dim2 = 5, spatial_dim3 = 3].
An input layer will be implicitly created and the name of this input layer will be the same name as its parent prefixed with “input_”.
Then we add to the graph the MaxPool3D layer.

3 – Run graph

We call the forward method and retrieve the result with the “Prediction 5D” method.
This method returns two variables, the first one is the layer information (cluster composed of the layer name, the graph index and the shape of the output layer) and the second one is the prediction with a shape of [batch_size, channels, spatial_dim1, spatial_dim2, spatial_dim3].

 

MaxPool3D layer, batch and dimension

1 – Generate a set of data

We generate an array of data of type single and shape [numberof batch = 9, batch_size = 10, channels = 7, spatial_dim1 = 5, spatial_dim2 = 5, spatial_dim3 = 3].

2 – Define graph

First, we define the first layer of the graph which is an Input layer (explicit input layer method). This layer is setup as an input array shaped [channels = 7, spatial_dim1 = 5, spatial_dim2 = 5, spatial_dim3 = 3].
Then we add to the graph the MaxPool3D layer.

3 – Run graph

We call the forward method and retrieve the result with the “Prediction 5D” method.
This method returns two variables, the first one is the layer information (cluster composed of the layer name, the graph index and the shape of the output layer) and the second one is the prediction with a shape of [batch_size, channels, spatial_dim1, spatial_dim2, spatial_dim3].

 

Table of Contents