I got a great deal on a Dell XPS 13 7390 on Black Friday this year. It’s a regular 7390, not the 2-in-1 model. Still, it’s a really fantastic machine.

Summary

tf.keras.callbacks.EarlyStopping is used to terminate a training if a monitored quantity satisfies some criterion. For example, in the following code snippet, the training will stop before reaching the target epoch (10000 in this case) if the training loss has not improved for 3 epochs in a roll:

I wrote this post to remind myself of something.

Note: the content in this post was tested with the GPU version of TensorFlow 2.0.

Linux distribution: Arch Linux

Disclaimer: I use the Keras interface from TensorFlow 2.0.0-rc1, so I’m not sure if the content applies to the original Keras library or other versions of TensorFlow. And note that TensorFlow 2.0.0-rc1 uses eager-execution mode by default.

Disclaimer: I only use the GPU version of TensorFlow v2.0.0-rc1, so I don’t know if this works with other versions.