Calculating custom metrics with tf.estimator.DNNRegressor in TensorFlow 1.10

How to configure a tf.estimator.DNNRegressor to report different metrics like RMSE and MAE while evaluating?

tf.estimator.DNNRegressor

(One can ask the same question for tf.estimator.DNNClassifier and AUC metric)

tf.estimator.DNNClassifier

Note: I know that it must be done in tf.estimator.EstimatorSpec of
model_fn() for a custom tf.estimator.Estimator, but I don't know how to apply it for a
tf.estimator.DNNRegressor.

tf.estimator.EstimatorSpec

model_fn()

tf.estimator.Estimator

tf.estimator.DNNRegressor

1 Answer
1

you can use tf.contrib.estimator.add_metrics

Thanks for contributing an answer to Stack Overflow!

But avoid …

To learn more, see our tips on writing great answers.

Required, but never shown

Required, but never shown

By clicking "Post Your Answer", you acknowledge that you have read our updated terms of service, privacy policy and cookie policy, and that your continued use of the website is subject to these policies.