Hyperparameter

Learning Rate (from Stackoverflow)

Long
Long
Jul 26, 2017 · 1 min read

Epochs

Training iteration. In the training process , weights will update in every iteration, Under normal circumstances,loss is decrease meanwhile prediction accuracy increase.

If u find loss and accuracy trend are abnormal through many training iteration, u should stop and adjust hyperparameter or network architecture.

batch size(from Stackoverflow)

Welcome to a place where words matter. On Medium, smart voices and original ideas take center stage - with no ads in sight. Watch
Follow all the topics you care about, and we’ll deliver the best stories for you to your homepage and inbox. Explore
Get unlimited access to the best stories on Medium — and support writers while you’re at it. Just $5/month. Upgrade