|
- Interactive Development - Deep Java Library - DJL
Interactive Development This sections introduces the amazing toolkits that the DJL team developed to simplify the Java user experience Without additional setup, you can easily run the tool kits online and export the project into your local system Let’s get started Interactive JShell Interactive JShell is a modified version of JShell equipped with DJL features You can use the existing
- Documentation - Deep Java Library - DJL
Documentation This folder contains examples and documentation for the Deep Java Library (DJL) project JavaDoc API Reference Note: when searching in JavaDoc, if your access is denied, please try removing the string undefined in the url Demos Cheat sheet How to load a model How to collect metrics How to use a dataset How to set log level Dependency Management Cache Management Memory Management
- Development Guideline - Deep Java Library
Development Guideline Introduction Thank you for your interest in contributing to the Deep Java Library (DJL) In this document, we will cover everything you need to build, test, and debug your code when developing DJL Many of us use the IntelliJ IDEA IDE to develop DJL and we will sometimes mention it However, there is no requirement to use this IDE Coding Conventions When writing code for
- DJL Blogposts | djl
An Engine-Agnostic Deep Learning Framework in Java
- Why DJL Serving? - Deep Java Library
DJL Serving Overview DJL Serving is a high performance universal stand-alone model serving solution powered by DJL It takes a deep learning model, several models, or workflows and makes them available through an HTTP endpoint It can serve the following model types out of the box: PyTorch TorchScript model TensorFlow SavedModel bundle Apache MXNet model ONNX model (CPU) TensorRT model Python
- Inference Performance Optimization | djl
Multithreading Support One of the advantage of Deep Java Library (DJL) is Multi-threaded inference support It can help to increase the throughput of your inference on multi-core CPUs and GPUs and reduce memory consumption compared to Python
- Forecast the future in a timeseries data with Deep Java Library (DJL)
Forecast the future in a timeseries data with Deep Java Library (DJL) – Demonstration on M5forecasting and airpassenger datasests Junyuan Zhang, Kexin Feng Time series data are commonly seen in the world They can contain valued information that helps forecast for the future, monitor the status of a procedure and feedforward a control Generic applications includes the following: sales
- DJL - Jupyter notebooks - Deep Java Library
DJL - Jupyter notebooks Overview This folder contains tutorials that illustrate how to accomplish basic AI tasks with Deep Java Library (DJL) Beginner Tutorial More Tutorial Notebooks Run object detection with model zoo Load pre-trained PyTorch model Load pre-trained Apache MXNet model Transfer learning example Question answering example You can run our notebook online: Setup JDK 11 (not jre
|
|
|