MLPMnist-dl4j-example: MLPMNist Single Layer

This repo is a result of the blog post How to do Deep Learning for Java | Original post. Please refer to the post before considering using this repo to understand better on how to use the different aspects of it.

Previous home of the project: https://github.com/neomatrix369/awesome-ai-ml-dl/tree/master/examples/cloud-devops-infra/valohai/MLPMnist

Open built-in Terminal from the Android Studio or IntelliJ IDEA. If you prefer, use the terminal app on your computer. In the terminal window, cd to the project root directory MLPMnist-dl4j-example if not already in. (you can use IDE's run-configuration green run button, if you like.)

Build app

mvn package -Djavacpp.platform=linux-x86_64
or
mvn package -Djavacpp.platform=macos-x86_64
or
mvn package -Djavacpp.platform=windows-x86_64

Build app for the docker image

Build docker image

./buildUberJar.sh
./buildDockerImage.sh

Push to docker hub

./push-docker-image-to-hub.sh

Run app local

./runMLPMnist.sh --action train --output-dir /path/to/model/creation/folder

followed by

./runMLPMnist.sh --action evaluate --output-dir /path/to/model/folder

Model file created and seeked for in the respective cases, is called mlpmnist-single-layer.pb.

Run app in docker container

./runDockerContainer.sh

At the prompt in the container, do the same as mentioned in section Run app local.

Credits

This example has been inspired by the MLPMNist example example from DL4J. Credits to the original authors of this example on https://github.com/deeplearning4j/dl4j-examples,

License

Original authors of this DL4J example project remain the license holders of the work, although the original work has been modified to a good extent, and the Apache 2.0 License is cited for all those file/files in the matter (see License.txt in the root of the project). Exception to the above: four bash scripts have been authored by Mani Sarkar and have been cited under the Apache 2.0 license.

Resources

• Awesome AI/ML/DL resources
• Java AI/ML/DL resources
• Deep Learning and DL4J Resources
• Additional DL4J resources
  • Loss functions
    • Loss function Interface by DL4J
    • 5 Regression Loss Functions All Machine Learners Should Know
  • Evaluation
    • https://deeplearning4j.org/docs/latest/deeplearning4j-nn-evaluation
• Valohai resources
  • valohai | docs | blogs | GitHub | Videos | Showcase | About Valohai | Slack
  • Blog posts on how to use the CLI tool: 1 | 2
• Other resources
  • Awesome Graal | graalvm.org

Return to Awesome AI/ML/DL