Xenova/gelan-e_all

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

npm i @xenova/transformers

Ejemplo: Realizar detección de objetos con Xenova/gelan-e_all.

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

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

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

// 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 "car" at [157.78, 132.88, 223.89, 167.56] with score 0.89.
// Found "car" at [62.69, 120.29, 140.12, 146.40] with score 0.86.
// Found "bicycle" at [0.53, 180.42, 39.41, 204.48] with score 0.84.
// Found "bicycle" at [157.39, 163.91, 194.82, 189.06] with score 0.81.
// Found "person" at [192.77, 90.67, 207.29, 116.15] with score 0.80.
// Found "bicycle" at [124.00, 183.29, 162.22, 206.57] with score 0.78.
// Found "person" at [11.91, 164.63, 27.64, 200.17] with score 0.78.
// Found "person" at [166.75, 150.84, 187.49, 186.04] with score 0.74.
// ...