How to Create Neural Network for Recognizing Masks
[Part1] - Labeling

Description

Create annotation boxes to pictures. Generate anchors for image recognition

Parts

[Part1] - Labeling

[Part2] - Training & recognition

Supports

1. Labelbox

2. Supervise

Tech stack:

1. NodeJS
2. OpenCV4NodeJS
3. Elementtree
4. Keras-js

Installation

npm install

Env example:

DIRECTORY=mask_500
LABELS=mask

Running the app

1. Write to env file
2. Put pictures /train/images
3. Label this pictures using labelbox
4. Put ready json file to folder /train/annotations
5. npm run start

Results

Labesl ready for trainig using Yolov3.

Copy dataset folder to second project for training

Use Anchors from console or from json/detection_config as anchor for second project.

Contact company

• Fulcrum
  • Email: hello@fulcrum.rocks
  • Website: fulcrum.rocks
  • Blog: blog.fulcrum.rocks

Contact developer

• Serhii Kalachnikov
  • Email: serhii@fulcrum.rocks
  • Linkedin: Serhii Kalachnikov

Contributors

Pull requests are welcome. For major changes, please open an issue first to discuss what you would like to change.

License

MIT License