Welcome to our Support Center
Updated

SpatialDropout

Description

Setup and add the spatial dropout layer into the model during the definition graph step. Type : polymorphic.

 

Input parameters

 

Graph in : model architecture.

 parameters : layer parameters.

rate : float between 0 and 1, fraction of the input units to drop.
Default value “0”.
 data_format : enum, one of channels_last or channels_first (default) . The ordering of the dimensions in the inputs. channel_last corresponds to inputs with shape (batch, steps, features) while channels_first corresponds to inputs with shape (batch, features, steps).
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

3D tensor with shape :

  • If data_format = ‘channels_last’ : (samples, timesteps, channels).
  • If data_format = ‘channels_first’ : (samples, channels, timesteps).

4D tensor with shape :

  • If data_format is “channels_last” : (samples, rows, cols, channels).
  • If data_format is “channels_first” : (samples, channels, rows, cols).

5D tensor with shape :

  • If data_format = ‘channels_last’ : (samples, dim1, dim2, dim3, channels).
  • If data_format = ‘channels_first’ : (samples, channels, dim1, dim2, dim3).

Output shape

3D tensor with shape (with a 3D tensor as input) :

  • If data_format = ‘channels_last’ : (samples, timesteps, channels).
  • If data_format = ‘channels_first’ : (samples, channels, timesteps).

4D tensor with shape (with a 4D tensor as input) :

  • If data_format is “channels_last” : (samples, rows, cols, channels).
  • If data_format is “channels_first” : (samples, channels, rows, cols).

5D tensor with shape (with a 5D tensor as input) :

  • If data_format = ‘channels_last’ : (samples, dim1, dim2, dim3, channels).
  • If data_format = ‘channels_first’ : (samples, channels, dim1, dim2, 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).

SpatialDropout layer

1 – Generate a set of data

We generate an array of data of type single and shape [samples = 10, channels = 7, timesteps = 5].

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, timesteps = 5].
Then we add to the graph the SpatialDropout1D layer.

3 – Run graph

We call the forward method and retrieve the result with the “Prediction 3D” 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 [samples, channels, timesteps].

 

SpatialDropout layer, batch and dimension

1 – Generate a set of data

We generate an array of data of type single and shape [number of batch = 9, samples = 10, channels = 7, timesteps = 5].

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, timesteps = 5].
Then we add to the graph the SpatialDropout1D layer.

3 – Run graph

We call the forward method and retrieve the result with the “Prediction 3D” 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 [samples, channels, timesteps].

 

Tags:
Table of Contents