Welcome to our Support Center
Updated

Flatten

Description

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

 

Input parameters

 

Β Graph in : model architecture.

parameters : layer parameters.

Β data_format :Β enum, one ofΒ channels_lastΒ orΒ channels_firstΒ (default) . The ordering of the dimensions in the inputs.Β channel_lastΒ corresponds to inputs with shapeΒ (batch, steps, features)Β whileΒ channels_firstΒ corresponds to inputs with shapeΒ (batch, features, steps).
Default value β€œchannels_first”.
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 in/out paramΒ :

Β input_shapeΒ :Β integer array, shape (not including the batch axis). NB : To be used only if it is the first layer of the model.
Β output_behaviorΒ :Β enum, setup if the layer is an output layer.
Default β€œNot Output”.

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

 

Output parameters

 

Β Graph out : model architecture.

Dimension

Input shape

2D tensor with shape :

  • If data_format = β€˜channels_last’ : (batch_size, input_dim).
  • If data_format = β€˜channels_first’ : (batch_size, input_dim).

3D tensor with shape :

  • If data_format = β€˜channels_last’ : (batch_size, steps, features).
  • If data_format = β€˜channels_first’ : (batch_size, features, steps).

4D tensor with shape :

  • If data_format is β€œchannels_last” : (batch_size, rows, cols, channels).
  • If data_format is β€œchannels_first” : (batch_size, channels, rows, cols).

5D tensor with shape :

  • If data_format = β€˜channels_last’ : (batch_size, input_dim1, input_dim2, input_dim3, channels).
  • If data_format = β€˜channels_first’ : (batch_size, channels, input_dim1, input_dim2, input_dim3).

 

Output shape

2D tensor with shape (with a 2D tensor as input) :

  • If data_format = β€˜channels_last’ : (batch_size, new_input).
  • If data_format = β€˜channels_first’ : (batch_size, new_input).

2D tensor with shape (with a 3D tensor as input) :

  • If data_format = β€˜channels_last’ : (batch_size, steps * features).
  • If data_format = β€˜channels_first’ : (batch_size, features * steps).

2D tensor with shape (with a 4D tensor as input) :

  • If data_format is β€œchannels_last” : (batch_size, rows * cols * channels).
    If data_format is β€œchannels_first” : (batch_size, channels * rows * cols).

2D tensor with shape (with a 5D tensor as input) :

  • If data_format = β€˜channels_last’ : (batch_size, input_dim1 * input_dim2 * input_dim3 * channels).
  • If data_format = β€˜channels_first’ : (batch_size, channels * input_dim1 * input_dim2 * input_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).

Flatten layer

1 – Generate a set of data

We generate an array of data of type single and shape [batch_size, channels, rows, cols] (channel first is default layer configuration).
In case of channel last layer configuration, shape is [batch_size, rows, cols, channels].

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, rows = 5, cols = 3].
Then we add to the graph the Flatten layer.

3 – Run graph

We call the forward method and retrieve the result with the β€œPrediction 2D” 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 * rows * cols].

 

Flatten layer, batch and dimension

1 – Generate a set of data

We generate an array of data of type single and shape [number of batch, batch_size, channels, rows, cols] (channel first is default layer configuration).
In case of channel last layer configuration, shape is [number of batch, batch_size, rows, cols, channels].

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, rows = 5, cols = 3].
Then we add to the graph the Flatten layer.

3 – Run graph

We call the forward method and retrieve the result with the β€œPrediction 2D” 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 * rows * cols].

 

Tags:
Table of Contents