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

YOLOv8m-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/yolov8m-pose`.

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

// Load model and processor
const model_id = 'Xenova/yolov8m-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 [535.503101348877, 39.878777217864986, 644.8351860046387, 346.3689248085022] with score 0.655
  - nose: (444.86, 91.25) with score 0.912
  - left_eye: (449.55, 79.71) with score 0.912
  - right_eye: (436.53, 82.54) with score 0.689
  - left_ear: (457.66, 83.08) with score 0.774
  - left_shoulder: (476.25, 126.43) with score 0.984
  - right_shoulder: (419.05, 129.94) with score 0.675
  - left_elbow: (495.99, 180.55) with score 0.960
  - left_wrist: (504.15, 233.96) with score 0.888
  - left_hip: (469.08, 227.61) with score 0.961
  - right_hip: (428.82, 228.95) with score 0.821
  - left_knee: (474.97, 301.15) with score 0.919
  - right_knee: (434.24, 305.24) with score 0.704
  - left_ankle: (467.31, 384.83) with score 0.625
  - right_ankle: (439.09, 379.35) with score 0.378
Found person at [-0.08985519409179688, 56.876064038276674, 158.62728118896484, 371.25909755229947] with score 0.902
  - nose: (61.15, 102.21) with score 0.979
  - left_eye: (66.59, 91.92) with score 0.939
  - right_eye: (51.35, 95.02) with score 0.905
  - left_ear: (70.82, 97.11) with score 0.778
  - right_ear: (48.08, 97.46) with score 0.655
  - left_shoulder: (84.60, 139.95) with score 0.997
  - right_shoulder: (38.36, 139.32) with score 0.996
  - left_elbow: (98.25, 196.80) with score 0.990
  - right_elbow: (24.83, 188.15) with score 0.981
  - left_wrist: (103.38, 252.91) with score 0.977
  - right_wrist: (9.42, 233.04) with score 0.965
  - left_hip: (82.91, 247.50) with score 0.999
  - right_hip: (51.28, 248.31) with score 0.999
  - left_knee: (85.25, 326.65) with score 0.997
  - right_knee: (49.12, 330.50) with score 0.996
  - left_ankle: (96.84, 419.45) with score 0.964
  - right_ankle: (51.88, 416.89) with score 0.960
Found person at [109.41852569580077, 13.203005981445314, 505.06954193115234, 532.9905454635621] with score 0.911
  - nose: (126.16, 102.84) with score 0.586
  - left_eye: (125.44, 84.07) with score 0.352
  - left_ear: (137.38, 77.79) with score 0.722
  - left_shoulder: (181.75, 122.32) with score 0.997
  - right_shoulder: (180.20, 152.15) with score 0.998
  - left_elbow: (262.31, 202.36) with score 0.996
  - right_elbow: (194.94, 277.60) with score 0.997
  - left_wrist: (298.87, 269.32) with score 0.987
  - right_wrist: (132.86, 281.44) with score 0.990
  - left_hip: (272.70, 284.47) with score 1.000
  - right_hip: (274.35, 307.48) with score 1.000
  - left_knee: (247.66, 441.74) with score 0.997
  - right_knee: (256.27, 500.82) with score 0.998
  - left_ankle: (340.54, 455.33) with score 0.848
  - right_ankle: (338.54, 543.24) with score 0.882
Found person at [425.35156250000006, 68.73829221725464, 640.3047943115234, 494.19192361831665] with score 0.901
  - nose: (425.40, 147.53) with score 0.995
  - left_eye: (432.33, 133.12) with score 0.985
  - right_eye: (410.70, 135.98) with score 0.969
  - left_ear: (440.72, 134.14) with score 0.901
  - right_ear: (400.69, 134.89) with score 0.800
  - left_shoulder: (455.11, 201.19) with score 1.000
  - right_shoulder: (368.64, 201.60) with score 0.999
  - left_elbow: (455.25, 292.03) with score 0.998
  - right_elbow: (350.65, 258.24) with score 0.989
  - left_wrist: (475.06, 370.36) with score 0.992
  - right_wrist: (398.78, 263.84) with score 0.975
  - left_hip: (441.94, 359.78) with score 1.000
  - right_hip: (384.06, 368.70) with score 1.000
  - left_knee: (462.74, 452.41) with score 0.998
  - right_knee: (395.50, 488.42) with score 0.997
  - left_ankle: (465.12, 540.38) with score 0.960
  - right_ankle: (433.43, 569.37) with score 0.938
```
</details>