import { AutoTokenizer, AutoProcessor, CLIPSegForImageSegmentation, RawImage } from '@huggingface/transformers';

// Load tokenizer, processor, and model
const tokenizer = await AutoTokenizer.from_pretrained('Xenova/clipseg-rd64-refined');
const processor = await AutoProcessor.from_pretrained('Xenova/clipseg-rd64-refined');
const model = await CLIPSegForImageSegmentation.from_pretrained('Xenova/clipseg-rd64-refined');

// Run tokenization
const texts = ['a glass', 'something to fill', 'wood', 'a jar'];
const text_inputs = tokenizer(texts, { padding: true, truncation: true });

// Read image and run processor
const image = await RawImage.read('https://github.com/timojl/clipseg/blob/master/example_image.jpg?raw=true');
const image_inputs = await processor(image);

// Run model with both text and pixel inputs
const { logits } = await model({ ...text_inputs, ...image_inputs });
// logits: Tensor {
//   dims: [4, 352, 352],
//   type: 'float32',
//   data: Float32Array(495616)[ ... ],
//   size: 495616
// }

You can visualize the predictions as follows:

// Visualize images
const preds = logits
  .unsqueeze_(1)
  .sigmoid_()
  .mul_(255)
  .round_()
  .to('uint8');

for (let i = 0; i < preds.dims[0]; ++i) {
  const img = RawImage.fromTensor(preds[i]);
  img.save(`prediction_${i}.png`);
}

Original	`"a glass"`	`"something to fill"`	`"wood"`	`"a jar"`
image	prediction_0	prediction_1	prediction_2	prediction_3

Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using 🤗 Optimum and structuring your repo like this one (with ONNX weights located in a subfolder named onnx).