Use Early Stopping to Halt the Training of Neural Networks At the Right Time

[wjunneng]

I have training and validation sets, can I add an early stopping strategy to avoid overfitting.

[wjunneng]

If I specify "epochs" and don't specify "batch_size", the model won't overfit。

[ourownstory]

Hi @wjunneng There is an old draft PR for this up: #289
If you like, you could bring it up to speed with the current state of the project and contribute the feature!