Welcome to our Support Center

BatchNormalization

Description

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

 

Input parameters

 

Graph in : model architecture.

parameters : layer parameters.

axis : integer, the axis that should be normalized (typically the features axis).
Default value “-1”.
momentum : float, momentum for the moving average.
Default value “0.99”.
epsilon : float, small float added to variance to avoid dividing by zero.
Default value “0.001”.
beta_initializer : enum, initializer for the beta weight.
Default value “Zeros”.
gamma_initializer : enum, initializer for the gamma weight.
Default value “Ones”.
optimizer :

 algorithm : enum, (name of optimizer) for optimizer instance.
Default value “adam”.
learning_rate : float, define the learning rate to use.
Default value “0.001”.
beta_1 : float, define the exponential decay rate for the 1st moment estimates.
Default value “0.9”.
beta_2 : float, define the exponential decay rate for the 2nd moment estimates.
Default value “0.999”.

training? : boolean, whether the layer is in training mode (can store data for backward).
Default value “True”.
store? : boolean, whether the layer stores the last iteration gradient (accessible via the “get_gradients” function).
Default value “False”.
update? : boolean, whether the layer’s variables should be updated during backward. Equivalent to freeze the layer.
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

Input tensor (of any rank).

 

Output shape

Same shape as input.

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).

BatchNormalization layer

1 – Generate a set of data

We generate an array of data of type single and shape [batch_size = 10, input_dim = 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 [input_dim = 5].
Then we add to the graph the BatchNormalization layer.

3 – Run graph

We call the forward method and retrieve the result with the “Prediction 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, input_dim].

 

BatchNormalization 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, batch_size = 10, input_dim = 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 [input_dim = 5].
Then we add to the graph the BatchNormalization layer.

3 – Run graph

We call the forward method and retrieve the result with the “Prediction 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, input_dim].

 

Table of Contents