O'Reilly logo

Hands-On Serverless Deep Learning with TensorFlow and AWS Lambda by Rustem Feyzkhanov

Stay ahead with the world's most comprehensive technology and business learning platform.

With Safari, you learn the way you learn best. Get unlimited access to videos, live online training, learning paths, books, tutorials, and more.

Start Free Trial

No credit card required

Training for MNIST

In this section, we'll discuss model training for MNIST:

  1. First, we start with importing the tensorflow library. For this example, we'll use the Keras deep learning framework, which makes it easy to set up layers for the neural network. In simple terms, Keras acts as a wrapper on top of TensorFlow, so everything is still based on TensorFlow.
  2. Next, we need to load data and present it in a binary format since the original image pixel values are 0 and 255. We'll also divide the dataset into training and test sets. This will allow us to measure the performance of the neural network. A good practice for the machine learning approach is to train the model on the training dataset and measure the final score on the test dataset. ...

With Safari, you learn the way you learn best. Get unlimited access to videos, live online training, learning paths, books, interactive tutorials, and more.

Start Free Trial

No credit card required