How to create tensor format for a CNN layer?

Friedemann

I plan to explain to my students how data can be processed using CNNs. For that purpose I would like to be able to explicitly convert a dataset with pixel values of images, like the csv Version of MNIST images, into tensor data that can be processed using a CNN. Is there any way to achieve this with RapidMiner? I tried the "ExamplesToTensor" operator, but the CNN layer complains, that the tensor format is for recurrent networks and cannot be processed by the CNN layer.

Friedemann

Question has been answered in another thread:

https://community.rapidminer.com/discussion/58052/error-when-using-convolutional-layer-message-new-shape-length-doesnt-match-original-length#latest

In a nutshell:

You have to specify the input shape manually! The default is set to "automatic". When switching off automatic mode a number of parameters can be set specifying how to map the data onto the tensor.

Important: This approach assumes that the data is stored as a sequence of rows in the csv and to have a single line per instance. Multi-channel data is represented as a "sequence" of complete instances per channel in the same line and indicated by the "depth" parameter of the input shape.

Friedemann

Question has been answered in another thread:

https://community.rapidminer.com/discussion/58052/error-when-using-convolutional-layer-message-new-shape-length-doesnt-match-original-length#latest

In a nutshell:

You have to specify the input shape manually! The default is set to "automatic". When switching off automatic mode a number of parameters can be set specifying how to map the data onto the tensor.

Important: This approach assumes that the data is stored as a sequence of rows in the csv and to have a single line per instance. Multi-channel data is represented as a "sequence" of complete instances per channel in the same line and indicated by the "depth" parameter of the input shape.