Difference between DNNRegressor, DNNClassifier and DNNEstimator - TensorFlow

Question

I'm new on TensorFlow and I'd like to know what is the difference between DNNRegressor, DNNClassifier and DNNEstimator. I can't find it in the official guide.

Answer 1

DNN stands for "deep neural network," which is a neural network with multiple layers. A DNNClassifier predicts which category an input sample belongs to. If you want an estimator to classify animals based on images from a zoo, you'd create a DNNClassifier.

A DNNRegressor is similar, but instead of predicting a category, it predicts a numeric value in a continuous range. If you want an application to predict tomorrow's stock price, you'd create a DNNRegressor.

A DNNEstimator can serve as a DNNClassifier or a DNNRegressor depending on how you configure it. This is very complicated to use, so if you're starting out, I'd stick with a DNNClassifier or DNNRegressor.