Training

Once you've created a cluster using the steps in Amazon EKS Setup, you can use it to run training jobs. For training, you can use either a CPU, GPU, or distributed GPU example depending on the nodes in your cluster. The topics in the following sections show how to use Apache MXNet (Incubating), PyTorch, TensorFlow, and TensorFlow 2 training examples.

Contents

• CPU Training
• GPU Training
• Distributed GPU Training