Hands-On Machine Learning with TensorFlow.js

MobileNet in tfjs-models

For example, here is some code that uses the MobileNet model. It's a small, low-latency model parameterized for a resource-constrained environment:

<script src="https://cdn.jsdelivr.net/npm/@tensorflow/tfjs@1.0.1"> </script>
<!-- Load the MobileNet model from jsDelivr -->
<script src="https://cdn.jsdelivr.net/npm/@tensorflow-models/mobilenet@1.0.0"> </script>

<script>
  const img = document.getElementById('img');

  // Load the model asynchronously.
  mobilenet.load().then(model => {
    // Classify the image.
    model.classify(img).then(predictions => {
      console.log('Predictions: ');
      console.log(predictions);
    });
  });
</script>

As it shows, you can use TensorFlow.js and the MobileNet model without training a model or even ...