<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Onnx on Noureddine RAMDI</title><link>https://ramdi.fr/tags/onnx/</link><description>Recent content in Onnx on Noureddine RAMDI</description><generator>Hugo</generator><language>en</language><lastBuildDate>Sat, 23 May 2026 20:41:27 +0000</lastBuildDate><atom:link href="https://ramdi.fr/tags/onnx/index.xml" rel="self" type="application/rss+xml"/><item><title>Open Photo AI: An open-source cross-platform desktop app for AI-powered photo enhancement</title><link>https://ramdi.fr/github-stars/open-photo-ai-an-open-source-cross-platform-desktop-app-for-ai-powered-photo-enhancement/</link><pubDate>Sat, 23 May 2026 20:41:14 +0000</pubDate><guid>https://ramdi.fr/github-stars/open-photo-ai-an-open-source-cross-platform-desktop-app-for-ai-powered-photo-enhancement/</guid><description>Open Photo AI is an open-source desktop app using ONNX AI models for photo enhancement with a unique model selection system and autopilot mode. It supports Windows, macOS, and Linux.</description></item><item><title>GoMLX: Bringing PyTorch-Level Machine Learning to Go with OpenXLA and WASM</title><link>https://ramdi.fr/github-stars/gomlx-bringing-pytorch-level-machine-learning-to-go-with-openxla-and-wasm/</link><pubDate>Tue, 05 May 2026 22:24:55 +0000</pubDate><guid>https://ramdi.fr/github-stars/gomlx-bringing-pytorch-level-machine-learning-to-go-with-openxla-and-wasm/</guid><description>GoMLX is a Go-native machine learning framework offering automatic differentiation, multi-backend support including OpenXLA acceleration, and ONNX compatibility. It enables training and inference of LLMs like GPT-2 entirely in Go, with a pure-Go backend for WASM.</description></item><item><title>SmartScan Android: on-device AI for offline media search and clustering</title><link>https://ramdi.fr/github-stars/smartscan-android-on-device-ai-for-offline-media-search-and-clustering/</link><pubDate>Tue, 05 May 2026 13:37:39 +0000</pubDate><guid>https://ramdi.fr/github-stars/smartscan-android-on-device-ai-for-offline-media-search-and-clustering/</guid><description>SmartScan Android runs vector similarity search and clustering entirely on-device using ONNX Runtime, enabling offline private text and reverse-image search over local media.</description></item><item><title>Deploying RL-trained motion tracking policies on legged robots with motion_tracking_controller</title><link>https://ramdi.fr/github-stars/deploying-rl-trained-motion-tracking-policies-on-legged-robots-with-motion-tracking-controller/</link><pubDate>Mon, 04 May 2026 10:23:02 +0000</pubDate><guid>https://ramdi.fr/github-stars/deploying-rl-trained-motion-tracking-policies-on-legged-robots-with-motion-tracking-controller/</guid><description>motion_tracking_controller is a C++ ROS 2 package deploying RL-trained motion tracking policies on legged robots with ONNX inference and embedded robot control metadata.</description></item><item><title>onnxmltools: a Python toolkit for converting ML models to ONNX format</title><link>https://ramdi.fr/github-stars/onnxmltools-a-python-toolkit-for-converting-ml-models-to-onnx-format/</link><pubDate>Mon, 04 May 2026 10:23:02 +0000</pubDate><guid>https://ramdi.fr/github-stars/onnxmltools-a-python-toolkit-for-converting-ml-models-to-onnx-format/</guid><description>onnxmltools is a Python library for converting machine learning models from various frameworks into the ONNX format, enabling interoperability across runtimes and platforms.</description></item><item><title>ROMP: from real-time monocular 3D human mesh recovery to temporal tracking with dynamic cameras</title><link>https://ramdi.fr/github-stars/romp-from-real-time-monocular-3d-human-mesh-recovery-to-temporal-tracking-with-dynamic-cameras/</link><pubDate>Mon, 04 May 2026 10:03:52 +0000</pubDate><guid>https://ramdi.fr/github-stars/romp-from-real-time-monocular-3d-human-mesh-recovery-to-temporal-tracking-with-dynamic-cameras/</guid><description>ROMP evolves monocular multi-person 3D mesh recovery from single-frame regression to temporal tracking under dynamic cameras, packaged with ONNX acceleration and Docker support.</description></item></channel></rss>