not blurring faces

[tfaehse]

not blurring faces

[tfaehse]

That's regrettable. I've just tested this, for now just a few notes:

• my input data is fairly bad, since it's just my dashcam footage. Faces are rare, especially high-def profile shots like these. This will hopefully get better, especially also because of a really nice data donation I received.
• The _rect weights files don't perform well. I originally thought the higher resolution of training fixed-size images would benefit detection (especially of small objects, i.e. farther away plates), but Yolov5's mosaic data loader makes such a massive (positive) difference that it absolutely isn't the case.

For now, using _mosaic weights should yield better results. Long-term I'll hopefully be able to publish much better trained networks. I'll have a look at your PR and the other issue soon (I promise!), I'm unfortunately fairly busy at the moment.

edit: if you're looking to blur clips and only care about faces, that's a much simpler problem. There are some really nice, labelled datasets for facial recognition, in theory you can just train those with YOLOv5, name the face class "face" and drop them into the weights folder.

[joshinils]

hm, so you're saying I need different weights from somewhere?

I just did another test, footage from my bicycle driving past parked cars.
none of the (german) licence plates are blurred for any of the 8 weights files /(1080p|720p)(small|medium)(mosaic|rect).pt/

[tfaehse]

Could you send me a snippet of such a recording? I'm not saying results should be perfect, but I've tried lots of different input data by now and nothing at all sounds strange.
If you don't want to post such videos publicly feel free to message me privately, you can reach me at my git user at me or gmail dot com. I'll have a look!

[joshinils]

problem was my python packages and maybe using a threshold of 1