Skip to content
master
Switch branches/tags
Go to file
Code

Latest commit

* Adding initial file for section  and the Dataset

* Adding 'photo'

* Adding section 8.3: Language models and Dataset

* Adding Time Machine dataset util methods

* Removing unused code

* Fixed bug with type for List

* Removing unused spaces

* Adding functions of section 8.3 to TimeMachineUtils.java

* Moving plotting functions to its own class and also adding manager as parameter to some TimeMachineUtils functions

* Moving seqDataIter functions out of TimeMachine class to fix import error on the SeqDataLoader class

* Changing object[2] to djl pair

* Removing line space to re-run CI

* Changing return of loadDataTimeMachine to dataIter, Vocab instead of SeqDataLoader, Vocab and adding imports on TimeMachineUtils.java

* Removing redundant TimeMachineUtils import; changed block comments on functions to javadoc format; modified output strings to look uniformly and better
eca0176

Git stats

Files

Permalink
Failed to load latest commit information.

README.md

Dive into Deep Learning (Java version)

This project is modified from the original Dive Into Deep Learning book by Aston Zhang, Zachary C. Lipton, Mu Li, Alex J. Smola and all the community contributors. GitHub of the original book: https://github.com/d2l-ai/d2l-en. We have adapted the book to to use Java and the Deep Java Library(DJL).

All the notebook here can be downloaded and run using Java Kernel. We also compiled the book into a website.

This project is currently being developed and maintained by AWS and the DJL community.

How to run Jupyter Notebook in Java

Online

You can run online by clicking: Binder

Or Colab: Colab

Local

Please follow the instruction here for how to run notebook using Java kernel.

How to contribute to this book

Please follow the contributor guide here

We have the following chapters implemented

About Deep Java Library

Deep Java Library (DJL) is a Deep Learning Framework written in Java, supporting both training and inference. DJL is built on top of modern Deep Learning frameworks (TenserFlow, PyTorch, MXNet, etc). You can easily use DJL to train your model or deploy your favorite models from a variety of engines without any additional conversion. It contains a powerful ModelZoo design that allows you to manage trained models and load them in a single line. The built-in ModelZoo currently supports more than 70 pre-trained and ready to use models from GluonCV, HuggingFace, TorchHub and Keras.

Follow our GitHub, demo repository, Slack channel and twitter for more documentation and examples of DJL!