I Built a Neural Network Engine in C# That Runs in Your Browser - No ONNX Runtime, No JavaScript Bridge, No Native Binaries
A new neural network engine called SpawnDev.ILGPU.ML has been developed to run in web browsers using C#. It eliminates the need for ONNX Runtime, JavaScript bridges, and native binaries, allowing for seamless execution of neural networks directly from a single C# codebase. The library supports multiple backends and offers various inference pipelines for tasks like image classification and background removal.
- ▪SpawnDev.ILGPU.ML runs neural networks in the browser without requiring ONNX Runtime or JavaScript bridges.
- ▪The library supports six backends, including WebGPU and WebGL, and allows for direct GPU rendering to HTML canvases.
- ▪It features five validated inference pipelines for tasks such as image classification and monocular depth estimation.
Opening excerpt (first ~120 words) tap to expand
try { if(localStorage) { let currentUser = localStorage.getItem('current_user'); if (currentUser) { currentUser = JSON.parse(currentUser); if (currentUser.id === 3764795) { document.getElementById('article-show-container').classList.add('current-user-is-article-author'); } } } } catch (e) { console.error(e); } Todd Tanner Posted on May 23 I Built a Neural Network Engine in C# That Runs in Your Browser - No ONNX Runtime, No JavaScript Bridge, No Native Binaries #csharp #machinelearning #webassembly #blazor Eight months ago, the creator of ILGPU told me that supporting Blazor WebAssembly as a backend would be too difficult. Today I shipped SpawnDev.ILGPU.ML 4.0.0-preview.4 to NuGet. It runs neural networks in your browser, on your laptop, and on your server - from a single C# codebase.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at DEV.to (Top).
Discussion
0 commentsMore from DEV.to (Top)
