onnxruntime-web

import * as ort from 'onnxruntime-web'; const runModel = async () => { // Configure ONNX Runtime Web environment (optional, for performance) // Enable WebAssembly SIMD for performance if supported ort.env.wasm.simd = true; // Set number of threads for WebAssembly (auto-detected if 0, 1 disables multithreading) // Requires cross-origin isolation headers for multithreading in browsers. ort.env.wasm.numThreads = Math.min(navigator.hardwareConcurrency / 2, 4) || 1; // Example setting // Choose execution providers. WebGPU is experimental but offers best performance. // Fallback to WASM (CPU) if WebGPU is not available. const executionProviders = ['webgpu', 'wasm']; // Load a sample ONNX model (e.g., a simple identity model from a public URL). // In a real app, place your model.onnx in the 'public' folder or fetch from a CDN. const modelPath = 'https://onnxruntime.ai/onnx-models/mnist-8.onnx'; // Example model let session; try { session = await ort.InferenceSession.create(modelPath, { executionProviders }); console.log('Inference session created successfully.'); } catch (e) { console.error(`Failed to create inference session: ${e.message}. Trying WASM only.`); // Fallback if initial providers fail session = await ort.InferenceSession.create(modelPath, { executionProviders: ['wasm'] }); console.log('Inference session created with WASM fallback.'); } // Create a dummy input tensor for an MNIST model (28x28 grayscale image). // Model expects input 'Input3' of shape [1, 1, 28, 28] and type 'float32'. const inputData = new Float32Array(1 * 1 * 28 * 28).fill(0.5); // Example: fill with 0.5 const inputTensor = new ort.Tensor('float32', inputData, [1, 1, 28, 28]); // Prepare input feeds, matching model's expected input names. const feeds = { 'Input3': inputTensor }; // Run inference. try { const results = await session.run(feeds); // Get output (model has one output 'Plus21_Output'). const outputTensor = results['Plus21_Output']; console.log('Inference results:', outputTensor.data); console.log('Output tensor type:', outputTensor.type); console.log('Output tensor dimensions:', outputTensor.dims); } catch (e) { console.error(`Failed to run inference: ${e.message}`); } }; runModel();