tfjs-yolo-tiny

1.0.1 • Public • Published

⚡️ Fast In-Browser Object Detection 👀

Detect objects in images right in your browser using Tensorflow.js! Currently takes ~800ms to analyze each frame on Chrome MBP 13" mid-2014.

Supports Tiny YOLO, as of right now, tfjs does not have support to run any full YOLO models (and your user's computers probably can't handle it either).

Demo

Check out the Live Demo

(You can only get so far with 1 FPS)

yolo person detection

Install

Yarn

yarn add tfjs-yolo-tiny

Or NPM

npm install tfjs-yolo-tiny

Usage Example

import yolo, { downloadModel } from 'tfjs-yolo-tiny';
 
const model = await downloadModel();
const inputImage = webcam.capture();
 
const boxes = await yolo(inputImage, model);
 
// Display detected boxes
boxes.forEach(box => {
  const {
    top, left, bottom, right, classProb, className,
  } = box;
 
  drawRect(left, top, right-left, bottom-top, `${className} ${classProb}`)
});

API Docs

yolo(input, model, options)

Args

Param Type Default Description
input tf.Tensor - Expected shape (1, 416, 416, 3) Tensor representing input image (RGB 416x416)
model tf.Model - Tiny YOLO tf.Model
[options] Object See Below Optional, Additional Configs

If you're using a custom Tiny YOLO model or want to adjust the default filtering cutoffs, you may do so by passing an additional options object.

Example: yolo(inputImage, model, { classProbThreshold: 0.8 });

Option Type Default Description
[options.classProbThreshold] Number 0.4 Filter out classes below a certain threshold
[options.iouThreshold] Number 0.4 Filter out boxes that have an IoU greater than this threadhold (refer to tf.image.nonMaxSuppression)
[options.filterBoxesThreshold] Number 0.01 Threshold to filter out box confidence * class confidence
[options.maxBoxes] Number 2048 Number of max boxes to return, refer to tf.image.nonMaxSuppression. Note: The model itself can only return so many boxes.
[options.yoloAnchors] tf.Tensor See src/postprocessing.js (Advanced) Yolo Anchor Boxes, only needed if retraining on a new dataset
[options.width] Number 416 (Advanced) If your model's input width is not 416, only if you're using a custom model
[options.height] Number 416 (Advanced) If your model's input height is not 416, only if you're using a custom model
[options.numClasses] Number 80 (Advanced) If your model has a different number of classes, only if you're using a custom model
[options.classNames] Array.<String> See src/coco_classes.js (Advanced) If your model has non-MSCOCO class names, only if you're using a custom model

Returns

Returns an array of objects.

Property Type Description
top Number Pixels from top of image where bounding box starts
left Number Pixels from left of image where bounding box starts
bottom Number Pixels from top of image where box ends.
right Number Pixels from left of image where box ends.
classProb Number Probability of the class in the bounding box.
className String Human name of the class.

downloadModel(url)

Args

Param Type Default Description
url string See DEFAULT_MODEL_LOCATION Tiny YOLO Model config path. See tf.loadModel

Returns

Returns a Promise that can resolve to a tf.Model.

Contributing

PR's are more than welcome! Perf improvement or better test coverage are probably the two biggest areas of immediate need. If you have thoughts on extensibility as well, feel free to open an issue!

Install Dependencies

yarn install

Run Tests

If you're running tests, make sure to yarn add @tensorflow/tfjs@0.7.0 so that you you don't get tfjs package not found errors. If you're developing, make sure to remove tfjs as a dependency, as it'll start using the local version of tfjs intead of the peer version.

Note: Test coverage is poor, definitely don't rely on them to catch your errors.

yarn test

Build

yarn build

Or during development, use watch mode, you can use the demo app to test out changes.

yarn watch

Package Sidebar

Install

npm i tfjs-yolo-tiny

Weekly Downloads

5

Version

1.0.1

License

MIT

Unpacked Size

248 kB

Total Files

5

Last publish

Collaborators

  • mikeshi42