Update README.md
Browse files
README.md
CHANGED
@@ -5,4 +5,56 @@ library_name: transformers.js
|
|
5 |
|
6 |
https://huggingface.co/hustvl/yolos-tiny with ONNX weights to be compatible with Transformers.js.
|
7 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
8 |
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](https://huggingface.co/docs/optimum/index) and structuring your repo like this one (with ONNX weights located in a subfolder named `onnx`).
|
|
|
5 |
|
6 |
https://huggingface.co/hustvl/yolos-tiny with ONNX weights to be compatible with Transformers.js.
|
7 |
|
8 |
+
## Usage (Transformers.js)
|
9 |
+
|
10 |
+
If you haven't already, you can install the [Transformers.js](https://huggingface.co/docs/transformers.js) JavaScript library from [NPM](https://www.npmjs.com/package/@huggingface/transformers) using:
|
11 |
+
```bash
|
12 |
+
npm i @huggingface/transformers
|
13 |
+
```
|
14 |
+
|
15 |
+
**Example:** Perform object detection with `Xenova/yolos-tiny`.
|
16 |
+
|
17 |
+
```js
|
18 |
+
import { pipeline } from "@huggingface/transformers";
|
19 |
+
|
20 |
+
const detector = await pipeline("object-detection", "Xenova/yolos-tiny");
|
21 |
+
|
22 |
+
const image = "https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/cats.jpg";
|
23 |
+
const output = await detector(image, { threshold: 0.9 });
|
24 |
+
console.log(output);
|
25 |
+
```
|
26 |
+
|
27 |
+
<details>
|
28 |
+
|
29 |
+
<summary>Example output</summary>
|
30 |
+
|
31 |
+
```
|
32 |
+
[
|
33 |
+
{
|
34 |
+
score: 0.9921281933784485,
|
35 |
+
label: "remote",
|
36 |
+
box: { xmin: 32, ymin: 78, xmax: 185, ymax: 117 },
|
37 |
+
},
|
38 |
+
{
|
39 |
+
score: 0.9884883165359497,
|
40 |
+
label: "remote",
|
41 |
+
box: { xmin: 324, ymin: 82, xmax: 376, ymax: 191 },
|
42 |
+
},
|
43 |
+
{
|
44 |
+
score: 0.9197800159454346,
|
45 |
+
label: "cat",
|
46 |
+
box: { xmin: 5, ymin: 56, xmax: 321, ymax: 469 },
|
47 |
+
},
|
48 |
+
{
|
49 |
+
score: 0.9300552606582642,
|
50 |
+
label: "cat",
|
51 |
+
box: { xmin: 332, ymin: 25, xmax: 638, ymax: 369 },
|
52 |
+
},
|
53 |
+
]
|
54 |
+
```
|
55 |
+
|
56 |
+
</details>
|
57 |
+
|
58 |
+
---
|
59 |
+
|
60 |
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](https://huggingface.co/docs/optimum/index) and structuring your repo like this one (with ONNX weights located in a subfolder named `onnx`).
|