------------------------------------ Powering edge AI: welcome to Aidge! ------------------------------------ :Release: |version| :Date: |today| .. grid:: 1 2 2 3 :margin: 4 4 0 0 :gutter: 1 .. grid-item-card:: :octicon:`desktop-download` Install :link: source/GetStarted/install :link-type: doc Find your configuration and requirements. .. grid-item-card:: :octicon:`table` Quick Start :link: https://eclipse.dev/aidge/source/Tutorial/101_first_step.html Build, train and deploy your first network. .. grid-item-card:: :octicon:`checklist` User Guide :link: source/UserGuide/index :link-type: doc The main hub for detailed usage explanations. .. grid-item-card:: :octicon:`book` API Reference :link: source/API/index :link-type: doc Details every module, class and function. .. grid-item-card:: :octicon:`light-bulb` Tutorials :link: source/Tutorial/index :link-type: doc Hands-on learning. .. grid-item-card:: :octicon:`comment` Exchange forum :link: https://chat.eclipse.org/#/room/#aidge:matrix.eclipse.org Exchange with the team and other users over features. What is Aidge? ============== Aidge is an innovative, open-source framework designed to streamline and accelerate the deployment of Deep Neural Networks onto diverse hardware targets. In today's rapidly evolving AI landscape, moving from a trained model to a high-performance, production-ready application can be a complex and time-consuming process. Aidge addresses this challenge by providing a comprehensive set of tools and methodologies, specifically built for embedded systems and edge devices where resource constraints are paramount, to efficiently **analyze, optimize, validate and deploy your AI models**. - Ready to get started? Dive into our `101 tutorial `__! .. .. image:: /source/_static/aidge_snapshot.png :scale: 65% Why Aidge stands out? ===================== .. _why-aidge: End-to-end workflow integration ------------------------------- Traditional embedded AI development often grapples with fragmented workflows and opaque "black-box" solutions. Aidge provides an open and end-to-end integrated platform, streamlining the entire AI lifecycle from model design to optimized deployment. Its open and `modular architecture `__ ensures a high degree of **interoperability with existing development environments** and toolchains (PyTorch, ONNX, etc.), allowing seamless integration into your current ecosystem. - Learn how Aidge works with `ONNX `__ . Efficient optimization techniques --------------------------------- Aidge offers **proven optimization techniques** like **quantization, pruning and compression** to significantly reduce model size and energy consumption, without compromising performance. Our methods are **reproducible and work independently of any hardware SDKs**. - Dive into our tutorial to master `post-training quantization `__. Advanced model transformations ------------------------------- Our **intermediate representation** provides powerful capabilities for graph manipulation and transformation, allowing precise adaptation of AI models for embedded hardware constraints. - Master `graph matching `__ and `tiling `__ with our tutorials. Multi-platform deployment ------------------------- Aidge ensures **transparent code generation**, providing clear visibility into the final implementation, fostering trust and ease of debugging. Through its **unified edge AI deployment framework**, it facilitates **multi-platform deployment** of optimized models across diverse target architectures. - Our tutorials guide you through `C++ deployment `__ and `TensorRT integration `__. Deep model insights -------------------- Aidge provides comprehensive tools for model analysis and optimization, helping you **understand model complexity and resource footprint**. The **Aidge Model Explorer**, built on the Google Model Explorer, offers intuitive navigation through model architectures. Additionally, Aidge makes it easy to **benchmark model performance** by enabling straightforward comparisons with other frameworks, including PyTorch, and ONNXRT. - Check out our tutorial on `static model analysis `__ Our commitments =============== Embracing Openness ------------------ Aidge is a **collective asset** designed to facilitate the deployment of edge AI. Proudly hosted by the `Eclipse Foundation `__, it ensures complete vendor neutrality and transparent governance. This open-source model fosters a vibrant, **community-driven development**, where diverse contributions converge to build a robust and widely accessible platform for sustainable edge AI innovation. Building Trustworthiness ------------------------- In an era where **trust in AI is paramount**, Aidge stands out by making **every element of its toolchain open and traceable**. This unwavering commitment to transparency builds profound **trust** among developers and users alike. By providing a clear, auditable path for every process, Aidge aims at meeting stringent requirements needed for **certification** in critical embedded AI applications. Let's build embedded AI together! ================================= Why contribute to Aidge? ------------------------ Your expertise, innovative ideas, and passion would be huge plus to making Aidge the leading open-source platform for embedded AI. Whether you code, test, write documentation, or simply use Aidge, **there are countless ways to get involved**. Contributing to Aidge offers unique advantages: - **Real-world impact:** your contributions directly shape the future of embedded AI. - **Skill Enhancement:** learn from peers and deepen your technical expertise in a collaborative environment. - **Engaged community:** become part of a dynamic and welcoming open-source community. Connect with our community! --------------------------- Stay informed and get involved with the latest Aidge developments: - `GitLab Project `__: access the Aidge GitLab repository for code, issues, and discussions. - `Wiki Home `__: dive into detailed information and contributor guidelines. - `Developer Chat `__: engage directly with the Aidge developer community to participate in technical discussions. .. toctree:: :maxdepth: 1 :hidden: source/GetStarted/index.rst source/UserGuide/index.rst source/Tutorial/index.rst source/API/index.rst