How much memory is needed to run a CNN deep learning net with CSV data?

Friedemann
Friedemann New Altair Community Member
edited November 5 in Community Q&A
When running the MNIST example (CSV Version) with the manual input shape setting for "Convolutional Flattened"
(as described in here: https://community.rapidminer.com/discussion/58052/error-when-using-convolutional-layer-message-new-shape-length-doesnt-match-original-length#latest) using the CUDA backend I get an error message saying: Failed to allocate 1,685,712,896 bytes from HOST memory.

When running with the CPU backend, my machine simply runs out of memory and starts swapping (JVM memory is restricted to 10,000 MB and backend memory to 10G).

I guess that something is very wrong with the FeedForwardToCnnPreProcessor.


Tagged: