<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Licensing on DeepLearning.Earth</title><link>https://deeplearning.earth/tags/licensing/</link><description>Recent content in Licensing on DeepLearning.Earth</description><generator>Hugo -- gohugo.io</generator><language>en-us</language><lastBuildDate>Thu, 10 Sep 2026 09:00:00 +0700</lastBuildDate><atom:link href="https://deeplearning.earth/tags/licensing/index.xml" rel="self" type="application/rss+xml"/><item><title>Apache 2.0 covers oriented-det. It does not cover DOTA or HRSC.</title><link>https://deeplearning.earth/posts/2026-09-10_oriented_det_apache_license_versus_dota/</link><pubDate>Thu, 10 Sep 2026 09:00:00 +0700</pubDate><guid>https://deeplearning.earth/posts/2026-09-10_oriented_det_apache_license_versus_dota/</guid><description>Two things get collapsed into one sentence far too often: the software and the data the software was demonstrated on.
oriented-det is a sovereign, Apache 2.0 framework for oriented object detection. You can install it, audit it, fork it, run it on-prem or in a private cloud, and train it on imagery you have the right to use. That part is clear.
DOTA and HRSC2016 are not that grant. They are research datasets.</description></item></channel></rss>