We are doing the following Trained with GPUs using the GPU bindings. Serialize that model to disk. Using the CPU bindings we deserialize and get an error (see below) Is it possible to support this use case and is the GPU really required for scoring? [main] INFO org.nd4j.linalg.factory.Nd4jBacke…

This looks odd. The serialized model does not depend on the backend that was used to train it. What you’ve posted here isn’t enough to tell you what’s wrong. Can you tell us more about your problem?

GPU training, CPU scoring?

DL4J

dawood June 29, 2020, 1:09pm 3

Sorry, but I guess I posted this prematurely. The person seeing this can not reproduce. Thanks.

Topic		Replies	Views
CPU vs GPU difference DL4J	1	390	May 20, 2021
Only two threads are running when switching training to GPU DL4J	2	430	May 29, 2020
Please ensure that you have an nd4j backend on your classpath. Please see: https://deeplearning4j.konduit.ai/nd4j/backend ND4J	0	182	November 29, 2023
Configuring GPU-Backend in Maven Dependencies DL4J	10	1550	May 27, 2021
Basic deeplearning4j classification example DL4J	4	1084	February 3, 2020

GPU training, CPU scoring?

Related topics