eeerrrwwwuuu

I guess I removed all what is possible to leave just loop, which takes static image from ram disk, all stats are gone, but still gpu session takes about 1...

@naisy my bad, after rebooting computer it started to fly ! ;-) Thank You as always!

Ok I think I found solution : split_model: False but it gives 0.2 FPS :(

Ok, now I get the point, what would be the ideal solution to train model and get maximum performance from faster_rcnn on jetson tx2? Should I pick Nvidia implementation or...

Hmm.. 0.2 was on debug, in normal 2.1 fps, but video input was about HD size, I'm expecting 800x600 on input..so 3fps in possible. Ssd is much quicker I get...