Run deeplearning4j without GPU?
We do not imply anywhere in our documents that we only work on gpus. If for some reason you find that this is the case, could you please notify us in the github issue? https://github.com/deeplearning4j/deeplearning4j/issues
You only need the nd4j backend: http://nd4j.org/backend.html
Dl4j, unlike many other libraries, decouples the hardware implementation from the algorithms. The ticket here is our nd4j tensor library. Nd4j handles all calculations.
Think of it as "tensorflow / anano" if you like.
We are embedding all of our source binaries into the central part of maven.
Usually you only need: http://search.maven.org/#search%7Cga%7C1%7Cnd4j-native-platform
for cpu. GPU, we support 2 latest cuda versions: http://search.maven.org/#search%7Cga%7C1%7Cnd4j-cuda-7.5-platform
The same exact code that also works on android and pis: http://deeplearning4j.org/android
Same idea that you don't compile from source, just provide the correct backend.
source to share