When I tried to develop this application, I found that the photos are of different size and shape: some images are tall, some of them are wide, some of them are outside, some images are inside, and most of them are pictures of food. However, some are other, random things too. Another important aspect is, while training images varied in portrait/landscape and the number of pixels, most were roughly square, and many of them were exactly 500 x 375:
Figure 9: Resized figure (left the original and tall one, right the squared one)
As we have already seen, CNN cannot work with images with a heterogeneous size and shape. There are ...
