Logistic Regression with a Neural Network Mindset Assignment

I am currently working on this assignment, and am a little confused. The assignment says this:

Remember that train_set_x_orig is a numpy-array of shape (m_train, num_px, num_px, 3). For instance, you can access m_train by writing train_set_x_orig.shape[0]

We’re supposed to define the following variables:
m_train =

number of training examples

m_test =

number of test examples

num_px =

What’s the difference between the number of training examples and the number of test examples? I thought those were the same thing? Is the number of training examples the number of times we have the network iterate gradient descent? And the number of test examples the number of images we input to calculate the gradient for each iteration of descent? I would then assume that num_px is the number of elements within each image. Just a little unclear on the details, and would appreciate any input. Thanks!

First thing to note is that you filed this question under a completely generic category. You’ll have better luck getting answers if you file it under the appropriate Specialization and Course. I moved the thread for you to the Deep Learning Specialization - Course 1.

There are two separate datasets: the training dataset and the test dataset. Prof Ng explained this concept in the lectures. You use the training dataset to train the model (using back propagation and gradient descent) and then you use the test dataset to see how the trained model performs on data that it has never “seen” before.

Thank you for your reply! That makes sense.