Convolution Layer (legacy)

This node adds a Convolutional layer to the Deep Learning Model supplied by the input port. The layer performs convolution of the inputs (usually images) using a user defined number of convolution kernels.

The KNIME Deeplearning4J Integration has been marked as legacy with KNIME Analytics Platform 5.0 and will be deprecated in a future version. If you are using this extension in a production workflow, consider switching to one of the other deep learning integrations available in KNIME Analytics Platform.

Options

Number of Kernels: The number of convolution kernels to use. Hence, the number of feature maps produced by the layer.
Learning Rate: The learning rate that should be used for this layer.
Kernel Size: The size if the convolution kernel in each dimension. The values are given in pixels and are separated by a comma.
Stride: The stride for the convolution kernel in each dimension. Hence, the step size the kernel will be shifted over the input. The values are given in pixels and are separated by a comma.
Activation Function: The type of activation function that should be used for this layer.
Drop Out Rate: Drop Out probability for neurons.

Input Ports

: The model which will be extended by this layer.

Output Ports

: The model from the input port additionally containing this layer.

Views

This node has no views

Workflows

Developers

You want to see the source code for this node? Click the following button and we’ll use our super-powers to find it for you.

Installation

To use this node in KNIME, install the extension KNIME Deeplearning4J Integration (64bit only) (legacy) from the below update site following our NodePit Product and Node Installation Guide:

v5.3

A zipped version of the software site can be downloaded here.

Plugin provider: KNIME AG, Zurich, Switzerland

Plugin version: 5.3.0.v202312081534

On NodePit since: 2024-07-09

Last update: 2024-11-21

KNIME versions: Since v3.6

Deploy, schedule, execute, and monitor your KNIME workflows locally, in the cloud or on-premises – with our brand new NodePit Runner.

Try NodePit Runner!