Week 2 Lab - Logistic Regression with a Neural Network Mindset

For this lab when I run the code:

model(train_set_x, train_set_y, test_set_x, test_set_y, num_iterations = 2000, learning_rate = 0.005, print_cost = True)

I get a lower training set accuracy (91.3875%) and a much lower test set accuracy (34.0%) than I should be getting. How could I troubleshoot this?

I figured out it was because I was flattening the training and test sets incorrectly.

3 Likes