This project is an attempt to recreate google's Teachable Machine using tensorflow.js 🙂
Transfer Learning with MobileNet v3 in TensorFlow.js and saved graph model from TFHub.
Cick image and process image classification models in seconds without single line of code
Deployed here 👉 click here
We simply have a script tag in our HTML to grab the latest version of TensorFlow.js
In this case we simply reference the following:
<script src="https://cdn.jsdelivr.net/npm/@tensorflow/tfjs/dist/tf.min.js" type="text/javascript"></script>However, if you want to pull in a particular version of TensorFlow.js you can do so like this:
<script src="https://cdn.jsdelivr.net/npm/@tensorflow/[email protected]/dist/tf.min.js" type="text/javascript"></script>Optionally, if you want to include our TF.js visualization library you can do so using this import:
<script src="https://cdn.jsdelivr.net/npm/@tensorflow/tfjs-vis/dist/tfjs-vis.umd.min.js" type="text/javascript"></script>Visualizing Training ← More details here.
Nothing to see here. Just styles to make the demo look prettier. You can use or ignore these as you please.
This simply grabs a reference to a paragraph in the DOM and then prints out the TensorFlow.js version number to it once loaded.