Programming Assignment: Car detection with YOLO - CORRECTION

Section 2.1 - Inputs and Outputs states:

The input is a batch of images, and each image has the shape (m, 608, 608, 3)

This should read either:

The input is a batch of images, and each batch has the shape (m, 608, 608, 3)

or

The input is a batch of images, and each image has the shape (608, 608, 3)

Each image is of shape (608, 608, 3). Input to the model is a batch of m images. So, the dimension of the input batch is (m, 608, 608, 3)

I’ve notified the staff to fix the markdown. Thanks for bringing this up.