This experiment shows how you can use the power of Machine Learning directly in your browser to train and use a more advanced Convolutional Neural Network to classify clothing items from the Fashion MNIST dataset. Warning training is slow in browser, ideally you would do this in Node.js with CUDA installed for faster training. In the browser without CUDA it will take about 5 mins to train, and then inference will be super fast :-)
See console for even more outputs.
Input image is a 28x28 pixel greyscale image from the Fashion MNIST dataset - a piece of clothing!
Below you see what item the trained TensorFlow.js model has predicted from the input image.
It should get it right most of the time, but of course it's not perfect, so there will be times when it doesn't. Red is a wrong prediction, Green is a correct one.
Training model. Please wait. This can take around 5 minutes or so. Check console for progress (30 epochs total)
Change interval between classifications! Currently 1000ms