Xenova/yolov9-c_all

Si aún no lo has hecho, puedes instalar la biblioteca JavaScript Transformers.js desde NPM usando:

npm i @xenova/transformers

Ejemplo: Realizar detección de objetos con Xenova/yolov9-c_all.

import { AutoModel, AutoProcessor, RawImage } from '@xenova/transformers';

// Cargar modelo
const model = await AutoModel.from_pretrained('Xenova/yolov9-c_all', {
// quantized: false,    // (Opcional) Usar versión no cuantizada.
})

// Cargar procesador
const processor = await AutoProcessor.from_pretrained('Xenova/yolov9-c_all');
// processor.feature_extractor.size = { shortest_edge: 128 }    // (Opcional) Actualizar valor de redimensionado

// Leer imagen y ejecutar procesador
const url = 'https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/city-streets.jpg';
const image = await RawImage.read(url);
const inputs = await processor(image);

// Ejecutar detección de objetos
const threshold = 0.3;
const { outputs } = await model(inputs);
const predictions = outputs.tolist();

for (const [xmin, ymin, xmax, ymax, score, id] of predictions) {
  if (score < threshold) break;
  const bbox = [xmin, ymin, xmax, ymax].map(x => x.toFixed(2)).join(', ')
  console.log(`Found "${model.config.id2label[id]}" at [${bbox}] with score ${score.toFixed(2)}.`)
}
// Found "bicycle" at [0.64, 181.27, 38.81, 203.94] with score 0.84.
// Found "car" at [157.68, 137.26, 223.67, 167.39] with score 0.78.
// Found "bicycle" at [157.69, 167.86, 195.10, 188.92] with score 0.78.
// Found "bicycle" at [123.69, 184.40, 162.44, 206.26] with score 0.74.
// Found "car" at [62.47, 119.27, 139.17, 145.84] with score 0.73.
// Found "person" at [193.18, 91.03, 206.57, 116.17] with score 0.72.
// Found "traffic light" at [73.08, 20.15, 82.06, 35.85] with score 0.70.
// Found "person" at [11.45, 164.69, 27.88, 199.36] with score 0.69.
// ...