I read it 10 times but I am bit confused. In particular, I am refering to the third point.
- Okay, I get it.
- Get it too.
- Is that a solution for unseen images, right? Not for testing and training.
- I saw that, if you see vector are already normalized.
- Is there a better way of doing that? I am saying: put into the trash all code and re-doing.