File size: 2,144 Bytes
ed9f15f |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 |
/**
* Image Preprocessing - Prepare images for model inference
*/
import * as ort from 'https://cdn.jsdelivr.net/npm/onnxruntime-web@1.17.0/dist/esm/ort.min.js';
import { DETECTION_CONFIG } from '../config.js';
import { loadImage } from '../utils/imageUtils.js';
/**
* Preprocess image for SigLIP models
*/
export async function preprocessImage(imageData, size) {
const img = await loadImage(imageData);
// Create canvas and resize
const canvas = document.createElement('canvas');
canvas.width = size;
canvas.height = size;
const ctx = canvas.getContext('2d');
ctx.drawImage(img, 0, 0, size, size);
// Get image data
const imageDataObj = ctx.getImageData(0, 0, size, size);
const data = imageDataObj.data;
// Convert to float32 tensor [1, 3, size, size] and normalize
const float32Data = new Float32Array(3 * size * size);
const { mean, std } = DETECTION_CONFIG.siglip;
for (let i = 0; i < size * size; i++) {
float32Data[i] = ((data[i * 4] / 255.0) - mean[0]) / std[0]; // R
float32Data[size * size + i] = ((data[i * 4 + 1] / 255.0) - mean[1]) / std[1]; // G
float32Data[2 * size * size + i] = ((data[i * 4 + 2] / 255.0) - mean[2]) / std[2]; // B
}
return new ort.Tensor('float32', float32Data, [1, 3, size, size]);
}
/**
* Preprocess image for YOLO
*/
export async function preprocessImageYOLO(img, size) {
const canvas = document.createElement('canvas');
canvas.width = size;
canvas.height = size;
const ctx = canvas.getContext('2d');
ctx.drawImage(img, 0, 0, size, size);
const imageData = ctx.getImageData(0, 0, size, size);
const data = imageData.data;
const float32Data = new Float32Array(3 * size * size);
for (let i = 0; i < size * size; i++) {
float32Data[i] = data[i * 4] / 255.0;
float32Data[size * size + i] = data[i * 4 + 1] / 255.0;
float32Data[2 * size * size + i] = data[i * 4 + 2] / 255.0;
}
return new ort.Tensor('float32', float32Data, [1, 3, size, size]);
}
|