Implementing Callbacks in TensorFlow 2
Published:
Often when training neural networks, we will want to monitor the training process, record metrics, or make changes to the training process. In TensorFlow 2, callbacks can used to call utilities at certain points during training of a neural network. In this post, I’ll describe some of the common use cases of callbacks, show how to implement some of the standard callbacks with the built-in classes, and show how to write custom callbacks to make changes to the training process.