import { pipeline } from '@xenova/transformers';
// Create English text-to-speech pipeline
const synthesizer = await pipeline('text-to-speech', 'Xenova/mms-tts-eng');
// Generate speech
const output = await synthesizer('I love transformers');
// {
// audio: Float32Array(26112) [...],
// sampling_rate: 16000
// }
请参阅此处了解可用模型的列表。首先,我们在 Hugging Face Hub 上转换了约 1140 个模型中的 12 个。如果其中没有你想要的,可以使用我们的转换脚本自行转换。2. CLIPSeg 用于零样本图像分割。(#478)
import { AutoTokenizer, AutoProcessor, CLIPSegForImageSegmentation, RawImage } from '@xenova/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
// }
您可以按如下方式可视化预测结果:
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" |
---|---|---|---|---|
请查看此处以获取可用模型列表。
import { pipeline } from '@xenova/transformers';
// Create an image segmentation pipeline
const segmenter = await pipeline('image-segmentation', 'Xenova/segformer_b2_clothes');
// Segment an image
const url = 'https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/young-man-standing-and-leaning-on-car.jpg';
const output = await segmenter(url);
4. Table Transformer 用于从非结构化文档中提取表格。(#477)
import { pipeline } from '@xenova/transformers';
// Create an object detection pipeline
const detector = await pipeline('object-detection', 'Xenova/table-transformer-detection', { quantized: false });
// Detect tables in an image
const img = 'https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/invoice-with-table.png';
const output = await detector(img);
// [{ score: 0.9967531561851501, label: 'table', box: { xmin: 52, ymin: 322, xmax: 546, ymax: 525 } }]
import { pipeline } from '@xenova/transformers';
// Create an image classification pipeline
const classifier = await pipeline('image-classification', 'Xenova/dit-base-finetuned-rvlcdip');
// Classify an image
const url = 'https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/coca_cola_advertisement.png';
const output = await classifier(url);
// [{ label: 'advertisement', score: 0.9035086035728455 }]
import { pipeline } from '@xenova/transformers';
// Create a zero-shot image classification pipeline
const classifier = await pipeline('zero-shot-image-classification', 'Xenova/siglip-base-patch16-224');
// Classify images according to provided labels
const url = 'http://images.cocodataset.org/val2017/000000039769.jpg';
const output = await classifier(url, ['2 cats', '2 dogs'], {
hypothesis_template: 'a photo of {}',
});
// [
// { score: 0.16770583391189575, label: '2 cats' },
// { score: 0.000022096000975579955, label: '2 dogs' }
// ]
import { pipeline } from '@xenova/transformers';
// Create a masked language modelling pipeline
const pipe = await pipeline('fill-mask', 'Xenova/antiberta2');
// Predict missing token
const output = await pipe('Ḣ Q V Q ... C A [MASK] D ... T V S S');
分段任意模型(SAM)可以在给定输入图像和输入点的情况下,用于生成场景中对象的分割蒙版。请查看此处以获取完整的预转换模型列表。对该模型的支持已在#510中添加。
例子+源码: https://huggingface.co/spaces/Xenova/segment-anything-web
示例:使用 Xenova/slimsam-77-uniform 执行掩模生成。
import { SamModel, AutoProcessor, RawImage } from '@xenova/transformers';
const model = await SamModel.from_pretrained('Xenova/slimsam-77-uniform');
const processor = await AutoProcessor.from_pretrained('Xenova/slimsam-77-uniform');
const img_url = 'https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/corgi.jpg';
const raw_image = await RawImage.read(img_url);
const input_points = [[[340, 250]]] // 2D localization of a window
const inputs = await processor(raw_image, input_points);
const outputs = await model(inputs);
const masks = await processor.post_process_masks(outputs.pred_masks, inputs.original_sizes, inputs.reshaped_input_sizes);
console.log(masks);
// [
// Tensor {
// dims: [ 1, 3, 410, 614 ],
// type: 'bool',
// data: Uint8Array(755220) [ ... ],
// size: 755220
// }
// ]
const scores = outputs.iou_scores;
console.log(scores);
// Tensor {
// dims: [ 1, 1, 3 ],
// type: 'float32',
// data: Float32Array(3) [
// 0.8350210189819336,
// 0.9786665439605713,
// 0.8379436731338501
// ],
// size: 3
// }
这样可以将这三个预测蒙板可视化:
const image = RawImage.fromTensor(masks[0][0].mul(255));
image.save('mask.png');
Input image | Visualized output |
---|---|
|
|
接下来,选择 IoU 分数最高的通道,在本例中是第二个(绿色)通道。将其与原始图像相交,我们得到了该主题的孤立版本:
Selected Mask | Intersected |
---|---|
|
|
其他改进
修复了@Lian1230在#461中提交的关于Next.js Dockerfile的HOSTNAME 问题。
在#467中,在 README 中添加了空模板的链接。
在 #503 中添加对使用 ConvNextFeatureExtractor 处理非方形图像的支持
通过 #507 对远程 URL 中的修订进行编码
@Lian1230 在 #461 中进行了他们的首次贡献。
改进#485中的pipeline函数的类型。感谢@wesbos提出的建议!
意味着当您将鼠标悬停在类名称上时,您将获得示例代码来帮助您。
此版本是 #485 的后续版本,具有额外的以智能感知为中心的改进(请参阅 PR)。
添加对跨编码器模型的支持(+修复令牌类型 ID)(#501)
示例:使用 Xenova/ms-marco-TinyBERT-L-2-v2 进行信息检索。
import { AutoTokenizer, AutoModelForSequenceClassification } from '@xenova/transformers';
const model = await AutoModelForSequenceClassification.from_pretrained('Xenova/ms-marco-TinyBERT-L-2-v2');
const tokenizer = await AutoTokenizer.from_pretrained('Xenova/ms-marco-TinyBERT-L-2-v2');
const features = tokenizer(
['How many people live in Berlin?', 'How many people live in Berlin?'],
{
text_pair: [
'Berlin has a population of 3,520,031 registered inhabitants in an area of 891.82 square kilometers.',
'New York City is famous for the Metropolitan Museum of Art.',
],
padding: true,
truncation: true,
}
)
const { logits } = await model(features)
console.log(logits.data);
// quantized: [ 7.210887908935547, -11.559350967407227 ]
// unquantized: [ 7.235750675201416, -11.562294006347656 ]
全部0条评论
快来发表一下你的评论吧 !