Node.js client-side React App that uses TensorFlow model generated to recognize differences between a Coke bottle and a Green cup. You can find an in depth walkthrough for training a TensorFlow.js model here. Model generated using IBM's AI Machine-Learning (ML) cloud technology.

git clone the repo and cd into it by running the following command:

git clone https://github.com/dearmasm/object-detection-react.git
cd object-detection-react

Note: You’ll need to have Node 8.10.0 or later on your local development machine. You can use nvm (macOS/Linux) or nvm-windows to easily switch Node versions between different projects.

As example already comes with built-in model inside public directory, you do not need to create a model for intial use and testing. If you decide to generate a TensorFlow model using instructions referenced at the top of this documentation, then copy the model_web directory generated from the object detection walkthrough and paste it into the public folder of this repo.

Open http://localhost:3000 to view it in the browser.