misspelling in 07_Inception_Model

[thrillerist]

In tutorial 07_Inception_Model

We can see that it has been squeezed so it is rectangular, and the resolution has been reduced so the image has become more pixelated and grainy.

The best way to input images to this Inception model, is to pad the image so it is rectangular and then resize the image to 299 x 299 pixels.

I think it should be square rather than rectangular here.

[Hvass-Labs]

Thanks for the report. I haven't had time to fix this before now. This is such a tiny error that I thought about not fixing it. But I can see that it is confusing so I decided to fix it.

Although this was just 2 words that needed to be replaced, it is not something you can fix in 2 minutes. When I fix a Notebook I also have to rerun and test it. In this case it turned out that that classification scores were slightly different in TensorFlow v. 1.1 which meant that I also had to go through all the text and update that as well. So it ended up taking a long time to fix such a small error.