-
Quick start
-
API
-
-
-
- Get All Grad
- Get Grad by index
- Get Grad by name
- Get All Store Grad
- Get Store Grad by index
- Get Store Grad by name
- Get All Index/Name
- Get Index by name
- Get Name by index
- Get All "lda_coeff"
- Get "lda_coeff" by index
- Get "lda_coeff" by name
- Get All Layer Params
- Get Layer Params by index
- Get Layer Params by name
- Get All Opti Params
- Get Opti Params by index
- Get Opti Params by name
- Get All Train Status
- Get Train Status by index
- Get Train Status by name
- Get All Loss Type
- Get Model Name
- Get Platform
- Warning Param
- Get All Input Layer Shape
- Get All Output Layer Shape
- Get All Input Shape
- Get Input Shape by index
- Get Input Shape by name
- Get All Output Shape
- Get Output Shape by index
- Get Output Shape by name
- Get All Init Weight
- Get Init Weight by index
- Get Init Weight by name
- Get All Weights
- Get Weights by index
- Get Weights by name
- Get All Weights Shape
- Get Weights Shape by index
- Get Weights Shape by name
- Get All Update Weights
- Get Update Weights by index
- Get Update Weights by name
- Show All Articles ( 30 ) Collapse Articles
-
- Set All Store Grad
- Set Store Grad by index
- Set Store Grad by name
- Set All "lda_coeff"
- Set "lda_coeff" by index
- Set "lda_coeff" by name
- Set All Opti Params
- Set Opti Params by index
- Set Opti Params by name
- Set All Train Status
- Set Train Status by index
- Set Train Status by name
- Set All Loss Type
- Set Model Name
- Set Platform
- Warning Param
- Set All Update Weights
- Set Update Weights by index
- Set Update Weights by name
- Load All Weights
- Load All Weights Model
- Set All Random Weights
- Set Weights by index
- Set Weights by name
- Show All Articles ( 9 ) Collapse Articles
-
-
-
-
- PReLU 2D
- PReLU 3D
- PReLU 4D
- PReLU 5D
- AdditiveAttention
- Attention
- MutiHeadAttention
- Conv1D
- Conv2D
- Conv3D
- ConvLSTM1D
- ConvLSTM2D
- ConvLSTM3D
- Conv1DTranspose
- Conv2DTranspose
- Conv3DTranspose
- DepthwiseConv2D
- SeparableConv1D
- SeparableConv2D
- Dense
- Embedding
- BatchNormalization
- LayerNormalization
- Bidirectional
- GRU
- LSTM
- SimpleRNN
- Show All Articles ( 12 ) Collapse Articles
-
- PReLU 2D
- PReLU 3D
- PReLU 4D
- PReLU 5D
- AdditiveAttention
- Attention
- MultiHeadAttention
- Conv1D
- Conv2D
- Conv3D
- ConvLSTM1D
- ConvLSTM2D
- ConvLSTM3D
- Conv1DTranspose
- Conv2DTranspose
- Conv3DTranspose
- DepthwiseConv2D
- SeparableConv1D
- SeparableConv2D
- Dense
- Embedding
- BatchNormalization
- LayerNormalization
- Bidirectional
- GRU
- LSTM
- SimpleRNN
- Show All Articles ( 12 ) Collapse Articles
-
-
- PReLU 2D
- PReLU 3D
- PReLU 4D
- PReLU 5D
- AdditiveAttention
- Attention
- MultiHeadAttention
- Conv1D
- Conv2D
- Conv3D
- ConvLSTM1D
- ConvLSTM2D
- ConvLSTM3D
- Conv1DTranspose
- Conv2DTranspose
- Conv3DTranspose
- DepthwiseConv2D
- SeparableConv1D
- SeparableConv2D
- Dense
- Embedding
- BatchNormalization
- LayerNormalization
- Bidirectional
- GRU
- LSTM
- SimpleRNN
- Show All Articles ( 12 ) Collapse Articles
-
-
- PReLU 2D
- PReLU 3D
- PReLU 4D
- PReLU 5D
- AdditiveAttention
- Attention
- MultiHeadAttention
- Conv1D
- Conv2D
- Conv3D
- ConvLSTM1D
- ConvLSTM2D
- ConvLSTM3D
- Conv1DTranspose
- Conv2DTranspose
- Conv3DTranspose
- DepthwiseConv2D
- SeparableConv1D
- SeparableConv2D
- Dense
- Embedding
- BatchNormalization
- LayerNormalization
- Bidirectional
- GRU
- LSTM
- SimpleRNN
- Show All Articles ( 12 ) Collapse Articles
-
- PReLU 2D
- PReLU 3D
- PReLU 4D
- PReLU 5D
- AdditiveAttention
- Attention
- MultiHeadAttention
- Conv1D
- Conv2D
- Conv3D
- ConvLSTM1D
- ConvLSTM2D
- ConvLSTM3D
- Conv1DTranspose
- Conv2DTranspose
- Conv3DTranspose
- DepthwiseConv2D
- SeparableConv1D
- SeparableConv2D
- Dense
- Embedding
- BatchNormalization
- LayerNormalization
- Bidirectional
- GRU
- LSTM
- SimpleRNN
- Show All Articles ( 12 ) Collapse Articles
-
-
-
-
- Add
- AdditiveAttention
- AlphaDropout
- Attention
- Average
- AvgPool1D
- AvgPool2D
- AvgPool3D
- BatchNormalization
- Bidirectional
- Concatenate
- Conv1D
- Conv1DTranspose
- Conv2D
- Conv2DTranspose
- Conv3D
- Conv3DTranspose
- ConvLSTM1D
- ConvLSTM2D
- ConvLSTM3D
- Cropping1D
- Cropping2D
- Cropping3D
- Dense
- DepthwiseConv2D
- Dropout
- Embedding
- Flatten
- GaussianDropout
- GaussianNoise
- GlobalAvgPool1D
- GlobalAvgPool2D
- GlobalAvgPool3D
- GlobalMaxPool1D
- GlobalMaxPool2D
- GlobalMaxPool3D
- GRU
- Input
- LayerNormalization
- LSTM
- MaxPool1D
- MaxPool2D
- MaxPool3D
- MultiHeadAttention
- Multiply
- Permute3D
- Reshape
- RNN
- SeparableConv1D
- SeparableConv2D
- SimpleRNN
- SatialDropout
- Substract
- TimeDistributed
- UpSampling1D
- UpSampling2D
- UpSampling3D
- ZeroPadding1D
- ZeroPadding2D
- ZeroPadding3D
- Show All Articles ( 45 ) Collapse Articles
-
- AlphaDropout
- AvgPool1D
- AvgPool2D
- AvgPool3D
- BatchNormalization
- Bidirectional
- Conv1D
- Conv1DTranspose
- Conv2D
- Conv2DTranspose
- Conv3D
- Conv3DTranspose
- Cropping1D
- Cropping2D
- Cropping3D
- Dense
- DepthwiseConv2D
- Dropout
- Embedding
- Flatten
- GaussianDropout
- GaussianNoise
- GlobalAvgPool1D
- GlobalAvgPool2D
- GlobalAvgPool3D
- GlobalMaxPool1D
- GlobalMaxPool2D
- GlobalMaxPool3D
- GRU
- LayerNormalization
- LSTM
- MaxPool1D
- MaxPool2D
- MaxPool3D
- Permute3D
- Reshape
- RNN
- SeparableConv1D
- SeparableConv2D
- SimpleRNN
- SpatialDropout
- UpSampling1D
- UpSampling2D
- UpSampling3D
- ZeroPadding1D
- ZeroPadding2D
- ZeroPadding3D
- Show All Articles ( 32 ) Collapse Articles
-
-
-
GELU
Description
Setup and add gelu layer into the model during the definition graph step. Type : polymorphic.
Input parameters
Graph in : model architecture.
parameters : layer parameters.
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
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).
GELU 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, 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 GELU 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].
GELU 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, input_dim = 5].
2 – Define graph
First, we define the GELU 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 [input_dim = 5].
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 GELU 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].
GELU 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 GELU 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].