Cartucho

 Hello, so the problem is that you have an empty line in the end as you can see in the image. I will make my code robust to this...

Hello, you need to run an object detector over the images, the detector will give you 1 bounding box per object. Which detector are you using?

Yes, that's a great idea! Any recommendations/idea of how this should be implemented? - `Idea 0`: We could add an optional `difficult` on the end of each line of the...

@titikid Yes, I will implement it then. Thanks for noticing that, could you please tell me the output of: `python -m cProfile main.py -na -np` This way I will know...

@titikid I just added the difficult feature. Let me know if it works for you!

@titikid Thank you, I believe what's making it slow is writing up temporary files for computation, I believe if I load things into memory instead of files it should be...

Oh right... the script that is converting the `xml` to our format is not currently checking whether the detections are tagged as difficult or not. I can add that. Did...

Hello @kocica that sounds like a great idea! However how do you define which objects are `small`, `medium` and `large` in the image? Is there any standard rule? We could...

Hello, I do not understand what do you mean by `if I run train script`, could you please explain?

Hello, this script is based on [the following](https://github.com/Cartucho/mAP/blob/master/extra/intersect-gt-and-pred.py), right? It would be easier if you applied the changes directly to that script.