What kind of Keras data classification mode should I pick for my kind of machine learning problem?

So I have to come up with a machine learning model for a specific problem that I have. As far as I know, Keras allows for four different types of classification: Binary, Categorical, Multiclass Classification, and Multilabel Classification. However, I think my problem is so specific that I could use some guidance to see what is the correct type of classification or if I need a different type.

I've got a dataset of clothing items that are divided into two categories: Successful and non successful, and inside each folder I have a lot of other folders with every section of clothing (Shirt, jacket, pants, etc...), and inside, there's the pictures I'm going to train my model with. It's something like this:

Project
 |    
 +-- succesful
 |  |  
 |  +-- shirts
 |  |  |
 |  |  +-- images.png
 |  |
 |  +-- jackets
 |  |  |
 |  |  +-- images.png
 |  |
 |  +-- pants
 |  |  |
 |  |  +-- images.png
 |
 +-- unsuccesful
 |  |  
 |  +-- shirts
 |  |  |
 |  |  +-- images.png
 |  |
 |  +-- jackets
 |  |  |
 |  |  +-- images.png
 |  |
 |  +-- pants
 |  |  |
 |  |  +-- images.png

Any help or indications on where to look (i.e. a YouTube video where someone takes on a similar problem) is much appreciated.