This layer performs convolution in a single dimension with a factorization of the convolution kernel into two smaller kernels. Co…

This layer performs convolution in a single dimension with a factorization of the convolution kernel into two smaller kernels. Co…

This layer performs convolution in two dimensions with a factorization of the convolution kernel into two smaller kernels. Corres…

This layer performs convolution in two dimensions with a factorization of the convolution kernel into two smaller kernels. Corres…

The need for transposed convolutions generally arises from the desire to use a transformation going in the opposite direction of …

The need for transposed convolutions generally arises from the desire to use a transformation going in the opposite direction of …

Freezes the parameters of the selected layers. If the model is trained afterwards, the parameters of the selected layers are not …

This node executes a Keras deep learning network on a compatible external back end that can be selected by the user.

This node performs supervised learning on a Keras deep learning network.

This node reads a Keras deep learning network from an input file. The file can either contain a full, pre-trained network (.h5 fi…

Writes a Keras network to a file.

Similar to ordinary ReLUs but shifted by theta. f(x) = x for x > theta, f(x) = 0 otherwise . Corresponds to the Keras Thresholded…

This layer creates a convolution kernel that is convolved with the layer input over a single dimension. Corresponds to the Keras …

This layer creates a convolution kernel that is convolved with the layer input over a single dimension. Corresponds to the Keras …

This layer creates a convolution kernel that is convolved with the layer input over two dimensions. Corresponds to the Keras Conv…

This layer creates a convolution kernel that is convolved with the layer input over two dimensions. Corresponds to the Keras Conv…

Allows to manipulate the network architecture of a Keras deep learning model by choosing a new set of output tensors of the model…

Exponential linear units were introduced to alleviate the disadvantages of ReLU and LeakyReLU units, namely to push the mean acti…

A leaky ReLU is a rectified linear unit (ReLU) with a slope in the negative part of its input space. The motivation for leaky ReL…

Like the leaky ReLU, the parametric ReLU introduces a slope in the negative part of the input space to improve learning dynamics …