what is the real meaning of training steps in deep learning Tensorflow?

Question

I am following this tutorial about Google Cloud Platform (GCP) for deep learning. According to the tutorial it says

The --train_steps option specifies the total number of training batches.

However, in the code of the same tutorial it says

'--train_steps', help='Steps to run the training job for.'

Now, I am confused because I found several questions regarding this topic here in StackOverflow and other sources saying that the training steps corresponds to the number of iterations that the optimizer does to find the minimum. Can someone confirm which one of these three definitions is correct?

Answer 1

xerx is correct in that steps and batches are pretty much the same thing, and can be treated as doing exactly the same thing for your model. I write more about the training process, batch sizes, and overfitting in my book about stock prediction, which you can find here - it's great for learning Deep Learning.

Good Luck!