---
library_name: transformers.js
tags:
- pose-estimation
license: agpl-3.0
---

YOLOv8s-pose with ONNX weights to be compatible with Transformers.js.

## Usage (Transformers.js)

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/@xenova/transformers) using:
```bash
npm i @xenova/transformers
```

**Example:** Perform pose-estimation w/ `Xenova/yolov8s-pose`.

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

// Load model and processor
const model_id = 'Xenova/yolov8s-pose';
const model = await AutoModel.from_pretrained(model_id);
const processor = await AutoProcessor.from_pretrained(model_id);

// Read image and run processor
const url = 'https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/football-match.jpg';
const image = await RawImage.read(url);
const { pixel_values } = await processor(image);

// Set thresholds
const threshold = 0.3; // Remove detections with low confidence
const iouThreshold = 0.5; // Used to remove duplicates
const pointThreshold = 0.3; // Hide uncertain points

// Predict bounding boxes and keypoints
const { output0 } = await model({ images: pixel_values });

// Post-process:
const permuted = output0[0].transpose(1, 0);
// `permuted` is a Tensor of shape [ 8400, 56 ]:
// - 8400 potential detections
// - 56 parameters for each box:
//   - 4 for the bounding box dimensions (x-center, y-center, width, height)
//   - 1 for the confidence score
//   - 17 * 3 = 51 for the pose keypoints: 17 labels, each with (x, y, visibilitiy)

// Example code to format it nicely:
const results = [];
const [scaledHeight, scaledWidth] = pixel_values.dims.slice(-2);
for (const [xc, yc, w, h, score, ...keypoints] of permuted.tolist()) {
    if (score < threshold) continue;

    // Get pixel values, taking into account the original image size
    const x1 = (xc - w / 2) / scaledWidth * image.width;
    const y1 = (yc - h / 2) / scaledHeight * image.height;
    const x2 = (xc + w / 2) / scaledWidth * image.width;
    const y2 = (yc + h / 2) / scaledHeight * image.height;
    results.push({ x1, x2, y1, y2, score, keypoints })
}


// Define helper functions
function removeDuplicates(detections, iouThreshold) {
    const filteredDetections = [];

    for (const detection of detections) {
        let isDuplicate = false;
        let duplicateIndex = -1;
        let maxIoU = 0;

        for (let i = 0; i < filteredDetections.length; ++i) {
            const filteredDetection = filteredDetections[i];
            const iou = calculateIoU(detection, filteredDetection);
            if (iou > iouThreshold) {
                isDuplicate = true;
                if (iou > maxIoU) {
                    maxIoU = iou;
                    duplicateIndex = i;
                }
            }
        }

        if (!isDuplicate) {
            filteredDetections.push(detection);
        } else if (duplicateIndex !== -1 && detection.score > filteredDetections[duplicateIndex].score) {
            filteredDetections[duplicateIndex] = detection;
        }
    }

    return filteredDetections;
}

function calculateIoU(detection1, detection2) {
    const xOverlap = Math.max(0, Math.min(detection1.x2, detection2.x2) - Math.max(detection1.x1, detection2.x1));
    const yOverlap = Math.max(0, Math.min(detection1.y2, detection2.y2) - Math.max(detection1.y1, detection2.y1));
    const overlapArea = xOverlap * yOverlap;

    const area1 = (detection1.x2 - detection1.x1) * (detection1.y2 - detection1.y1);
    const area2 = (detection2.x2 - detection2.x1) * (detection2.y2 - detection2.y1);
    const unionArea = area1 + area2 - overlapArea;

    return overlapArea / unionArea;
}

const filteredResults = removeDuplicates(results, iouThreshold);

// Display results
for (const { x1, x2, y1, y2, score, keypoints } of filteredResults) {
    console.log(`Found person at [${x1}, ${y1}, ${x2}, ${y2}] with score ${score.toFixed(3)}`)
    for (let i = 0; i < keypoints.length; i += 3) {
        const label = model.config.id2label[Math.floor(i / 3)];
        const [x, y, point_score] = keypoints.slice(i, i + 3);
        if (point_score < pointThreshold) continue;
        console.log(`  - ${label}: (${x.toFixed(2)}, ${y.toFixed(2)}) with score ${point_score.toFixed(3)}`);
    }
}
```

<details>

<summary>See example output</summary>

```
Found person at [533.1403350830078, 39.96531672477722, 645.8853149414062, 296.1657429695129] with score 0.739
  - nose: (443.99, 91.98) with score 0.970
  - left_eye: (449.84, 85.01) with score 0.968
  - right_eye: (436.28, 86.54) with score 0.839
  - left_ear: (458.69, 87.08) with score 0.822
  - right_ear: (427.88, 89.20) with score 0.317
  - left_shoulder: (471.29, 128.05) with score 0.991
  - right_shoulder: (421.84, 127.22) with score 0.788
  - left_elbow: (494.03, 174.09) with score 0.976
  - right_elbow: (405.83, 162.81) with score 0.367
  - left_wrist: (505.29, 232.06) with score 0.955
  - right_wrist: (411.89, 213.05) with score 0.470
  - left_hip: (469.48, 217.49) with score 0.978
  - right_hip: (438.79, 216.48) with score 0.901
  - left_knee: (474.03, 283.00) with score 0.957
  - right_knee: (448.00, 287.90) with score 0.808
  - left_ankle: (472.06, 339.67) with score 0.815
  - right_ankle: (447.15, 340.44) with score 0.576
Found person at [0.03232002258300781, 57.89646775722503, 156.35095596313477, 370.9132190942764] with score 0.908
  - nose: (60.48, 105.82) with score 0.975
  - left_eye: (64.86, 100.59) with score 0.952
  - right_eye: (55.12, 100.60) with score 0.855
  - left_ear: (73.04, 101.96) with score 0.820
  - right_ear: (51.07, 103.28) with score 0.482
  - left_shoulder: (85.74, 137.77) with score 0.996
  - right_shoulder: (42.04, 137.63) with score 0.988
  - left_elbow: (101.10, 190.45) with score 0.988
  - right_elbow: (25.75, 186.44) with score 0.937
  - left_wrist: (115.93, 250.05) with score 0.975
  - right_wrist: (7.39, 233.44) with score 0.918
  - left_hip: (80.15, 242.20) with score 0.999
  - right_hip: (52.69, 239.82) with score 0.999
  - left_knee: (93.29, 326.00) with score 0.999
  - right_knee: (57.42, 329.04) with score 0.998
  - left_ankle: (100.24, 413.83) with score 0.992
  - right_ankle: (50.47, 417.93) with score 0.988
Found person at [106.16920471191406, 8.419264698028565, 515.0135803222656, 530.6886708259583] with score 0.819
  - nose: (134.03, 111.15) with score 0.921
  - left_eye: (137.51, 100.95) with score 0.824
  - right_eye: (131.82, 97.53) with score 0.489
  - left_ear: (147.19, 92.96) with score 0.792
  - left_shoulder: (188.28, 127.51) with score 0.993
  - right_shoulder: (181.81, 149.32) with score 0.995
  - left_elbow: (258.49, 199.10) with score 0.984
  - right_elbow: (181.43, 251.27) with score 0.988
  - left_wrist: (311.74, 257.93) with score 0.979
  - right_wrist: (129.68, 284.38) with score 0.984
  - left_hip: (267.43, 299.85) with score 1.000
  - right_hip: (277.05, 307.50) with score 1.000
  - left_knee: (232.15, 427.54) with score 0.999
  - right_knee: (278.99, 453.09) with score 0.999
  - left_ankle: (352.68, 457.89) with score 0.990
  - right_ankle: (362.15, 554.69) with score 0.993
Found person at [425.3855133056641, 73.76281919479369, 640.6651306152344, 502.32841634750366] with score 0.876
  - nose: (416.15, 149.68) with score 0.996
  - left_eye: (430.34, 139.56) with score 0.984
  - right_eye: (412.88, 142.56) with score 0.976
  - left_ear: (446.59, 142.21) with score 0.843
  - right_ear: (398.82, 144.52) with score 0.740
  - left_shoulder: (436.54, 197.92) with score 0.999
  - right_shoulder: (362.94, 210.20) with score 0.996
  - left_elbow: (460.06, 293.80) with score 0.992
  - right_elbow: (352.33, 262.09) with score 0.966
  - left_wrist: (491.33, 364.20) with score 0.986
  - right_wrist: (402.62, 272.23) with score 0.956
  - left_hip: (429.79, 354.94) with score 0.999
  - right_hip: (383.27, 372.77) with score 0.999
  - left_knee: (461.07, 437.73) with score 0.998
  - right_knee: (410.89, 522.05) with score 0.995
  - left_ankle: (460.74, 552.53) with score 0.966
  - right_ankle: (429.00, 560.54) with score 0.940
```
</details>