Skip to content

Latest commit

 

History

History
92 lines (52 loc) · 3.4 KB

README.en.md

File metadata and controls

92 lines (52 loc) · 3.4 KB

Request for support

TM2Scratch has been open source and free of charge since 2020, and is used in various places such as schools and various programming classes. In order to continue development, we need support from everyone who uses it. I would be very grateful if you could support me in the form of a cup of coffee.

TM2Scratch

Read this in other languages: English, 日本語.

TM2Scratch connects Google Teachable Machine 2 with Scratch 3. You can use image, audio recognition on Scratch project(Please use TMPose2Scratch for pose recognition).

License

TM2Scratch is under AGPL-3.0 license, open source and freely available to anyone. You can use it at your classes, workshops. Commercial usage is also accepted. If you or your students created something cool using TM2Scratch, please share it on SNS using hashtag #tm2scratch or let me know to any of these contacts.

How to use

Image recognition

  1. On Google Teachable Machine website, create an image classification model and upload it.

  2. Copy the sharable link.

  1. Open https://stretch3.github.io/ on Chrome browser.

  2. Open "Choose an Extension" window and select "TM2Scratch".

  3. Paste the shareble link into the text field of "image classification model URL" block.

  1. You can use the image recognition results with "when received image label" blocks.

Audio recognition

  1. On Google Teachable Machine website, create a sound classification model and upload it.

  2. Copy the sharable link.

  3. Open https://champierre.github.io/tm2scratch on Chrome browser.

  4. Open "Choose an Extension" window and select "TM2Scratch".

  5. Paste the shareble link into the text field of "sound classification model URL" block.

  1. You can use the sound recognition results with "when received sound label" blocks.

  1. NOTE The camera image that is trained on the Teachable Machine is a square, whereas the camera image that appears on the Scratch stage is a horizontal rectangle. Note that the horizontal edges of the camera image are ignored, and the image in the center is used to recognize. (This is not a problem as long as the object to be judged is in the center of the image.)

For Developers - How to run TM2Scratch extension on your computer

  1. Setup LLK/scratch-gui on your computer.

    % git clone [email protected]:LLK/scratch-gui.git
% cd scratch-gui
% npm install

  2. In scratch-gui folder, clone TM2Scratch. You will have tm2scratch folder under scratch-gui.

    % git clone [email protected]:champierre/tm2scratch.git

  3. Run the install script.

    % sh tm2scratch/install.sh

  4. Run Scratch, then go to http://localhost:8601/.

    % npm start

Demo & Links

  • TM2Scratch + micro:bit Extension