<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Inference on DeepLearning.Earth</title><link>https://deeplearning.earth/tags/inference/</link><description>Recent content in Inference on DeepLearning.Earth</description><generator>Hugo -- gohugo.io</generator><language>en-us</language><lastBuildDate>Sat, 11 Jul 2026 11:00:00 +0700</lastBuildDate><atom:link href="https://deeplearning.earth/tags/inference/index.xml" rel="self" type="application/rss+xml"/><item><title>Oriented-Det v0.1.1 — ProbIoU, MMRotate parity, and the updated zoo</title><link>https://deeplearning.earth/posts/2026-07-11_oriented-det_v0_1_1_prob_iou_mmrotate_parity_and_the_updated_zoo/</link><pubDate>Sat, 11 Jul 2026 09:00:00 +0700</pubDate><guid>https://deeplearning.earth/posts/2026-07-11_oriented-det_v0_1_1_prob_iou_mmrotate_parity_and_the_updated_zoo/</guid><description>Six weeks after v0.1.0, Oriented-Det v0.1.1 is on PyPI and tagged on GitHub. This is the release that packages the ProbIoU work, closes several MMRotate parity gaps in the training stack, and publishes the full eval-val protocol we have been using internally.
If you already read Rotated Faster R-CNN on DOTA without custom CUDA, you have seen the technical story behind the headline number. This post is the release note: what changed, how to upgrade, and what to watch for.</description></item></channel></rss>