Step1：建一个hook

early_stopping_hook = tf.contrib.estimator.stop_if_no_decrease_hook(            estimator=estimator,            metric_name='eval_loss',            max_steps_without_decrease=FLAGS.max_steps_without_decrease,            eval_dir=None,            min_steps=0,            run_every_secs=None,            run_every_steps=FLAGS.save_checkpoints_steps)

 

Step2：加到estimator.train里

estimator.train(input_fn=train_input_fn, max_steps=num_train_steps, hooks=[early_stopping_hook])