Marco Castelluccio

A GUI that shows the wrongly classified screenshots sounds fine to me. It should show the screenshots, their name, actual and predicted labels. Let's implement this first and then we...

Or also just a CLI that tells you which screenshots were wrongly classified, then you can just open the screenshots for yourself.

Yes, it would be preferable to reduce the number of dependencies. Use either Tkinter (no dependencies) or OpenCV (which will be a dependency after #128).

It sounds interesting, but maybe it's too much work?

Sounds good then!

> This is the output I am getting with overlapping threshold value of 0.5. Is it fine? Or should I make some changes. It looks OK to me. > Also...

(The label_persons/amitrockon.csv should be converted, labels.csv should be generated automatically)

Yes, we will have to add a new webdriver and use it in collect.py and update all the places where we were just expecting Firefox and Chrome.

> @marco-c having taken a look into it, I've found that safari and edge both are dependent on their respective os and cannot be run cross-platform. Should we still pursue...

Is it still available? I thought they stopped supporting Windows.