How to run estimator.train without saving checkpoints

Question

I'm looking for a way to implement a search of learning rate as described here: https://arxiv.org/pdf/1506.01186.pdf .

My network is implemented using estimator api and I'd like to stick to that, but unfortunately I'm not able to force estimator to skip saving checkpoints. Do you know a way to simply run a one epoch o training without saving the checkpoints?

Answer 1

According to the docs tf.estimator.RunConfig:

If both save_checkpoints_steps and save_checkpoints_secs are None, then checkpoints are disabled

So the code is following:

run_config = tf.estimator.RunConfig(save_summary_steps=None,
                                    save_checkpoints_secs=None)
estimator = tf.estimator.Estimator(model_fn=model_fn, config=run_config)