Experiment with different model architectures and see how each one behaves to image classfication.
While using the logistic regression to build cat vs. non-cat images and got a 68% accuracy.But now, this algorithm will now give you an 80% accuracy! By completing this exercise, I have:
-
Learn how to use all the helper functions you built in the previous LR model of any structure I want.
-
Experiment with different model architectures and see how each one behaves.
-
Recognize that it is always easier to build your helper functions before attempting to build a neural network from scratch.