SiaNet.Model.Layers Namespace

Classes


  Class Description
Public class Activation
Applies an activation function to an output.
Public class AvgPool1D
Average pooling for temporal data.
Public class AvgPool2D
Average pooling operation for spatial data.
Public class AvgPool3D
Average pooling operation for 3D data (spatial or spatio-temporal).
Public class BatchNorm
Batch normalization layer (Ioffe and Szegedy, 2014). Normalize the activations of the previous layer at each batch, i.e.applies a transformation that maintains the mean activation close to 0 and the activation standard deviation close to 1.
Public class Conv1D
1D convolution layer (e.g. temporal convolution). This layer creates a convolution kernel that is convolved with the layer input over a single spatial (or temporal) dimension to produce a tensor of outputs. If use_bias is True, a bias vector is created and added to the outputs. Finally, if activation is not None, it is applied to the outputs as well.
Public class Conv2D
2D convolution layer (e.g. spatial convolution over images). This layer creates a convolution kernel that is convolved with the layer input to produce a tensor of outputs. If use_bias is True, a bias vector is created and added to the outputs. Finally, if activation is not None, it is applied to the outputs as well.
Public class Conv3D
3D convolution layer (e.g. spatial convolution over volumes). This layer creates a convolution kernel that is convolved with the layer input to produce a tensor of outputs. If use_bias is True, a bias vector is created and added to the outputs. Finally, if activation is not None, it is applied to the outputs as well.
Public class Dense
Dense implements the operation: output = activation(dot(input, kernel) + bias) where activation is the element-wise activation function passed as the activation argument, kernel is a weights matrix created by the layer, and bias is a bias vector created by the layer (only applicable if use_bias is True).
Public class Dropout
Dropout consists in randomly setting a fraction rate of input units to 0 at each update during training time, which helps prevent overfitting.
Public class GlobalAvgPool1D
Global average pooling operation for temporal data.
Public class GlobalAvgPool2D
Global average pooling operation for spatial data.
Public class GlobalAvgPool3D
Global average pooling operation for 3D data (spatial or spatio-temporal).
Public class GlobalMaxPool1D
Global max pooling operation for temporal data.
Public class GlobalMaxPool2D
Global max pooling operation for spatial data.
Public class GlobalMaxPool3D
Global max pooling 3D data (spatial or spatio-temporal).
Public class MaxPool1D
Max pooling operation for temporal data.
Public class MaxPool2D
Max pooling operation for spatial data.
Public class MaxPool3D
Max pooling operation for 3D data (spatial or spatio-temporal).