Add support for Segformer

[xenova]

Example usage

Semantic segmentation

import { pipeline } from '@xenova/transformers';

const segmenter = await pipeline('image-segmentation', 'Xenova/segformer_b2_clothes', { quantized: false });

const url = "https://freerangestock.com/sample/139043/young-man-standing-and-leaning-on-car.jpg"
const output = await segmenter(url);
console.log(output)
// [
//   {
//     score: null,
//     label: 'Background',
//     mask: RawImage { ... }
//   },
//   {
//     score: null,
//     label: 'Hair',
//     mask: RawImage { ... }
//   },
//   ...
//   }
// ]

// Visualize images
for (const l of output) {
  l.mask.save(`${l.label}.png`);
}

Image classification

import { pipeline } from '@xenova/transformers';

const classifier = await pipeline('image-classification', 'Xenova/mit-b0');
const url = 'https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/tiger.jpg';
const output = await classifier(url);
console.log(output)
// [{ label: 'tiger, Panthera tigris', score: 0.5399330854415894 }]

[HuggingFaceDocBuilderDev]

The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update.