README.md

DJL - Jupyter notebooks

Overview

This folder contains tutorials that illustrate how to accomplish basic AI tasks with Deep Java Library (DJL).

List of tutorials

• Create your first neural network
• Train your first model
• Run image classification with your first model
• Run object detection with model zoo
• Load pre-trained MXNet model
• Transfer learning example
• Question answering example

Setup

JDK 11 (not jre)

JDK 11 (or above are required) to run the examples provided in this folder.

to confirm the java path is configured properly:

java --list-modules | grep "jdk.jshell"

> [email protected]

Install jupyter notebook on python3

pip3 install jupyter

Install IJava kernel for jupyter

git clone https://github.com/frankfliu/IJava.git
cd IJava/
./gradlew installKernel

Start jupyter notebook

jupyter notebook

Docker setup

You may want to use docker for simple installation or you are using Windows.

Run docker image

cd jupyter
docker run -itd -p 127.0.0.1:8888:8888 -v $PWD:/home/jupyter deepjavalibrary/jupyter

You can open the http://localhost:8888 to see the hosted instance on docker.

Build docker image by yourself

You can read Dockerfile for detail. To build docker image:

cd jupyter
docker build -t deepjavalibrary/jupyter .