melonwan
melonwan
No, the original code should run correctly. Sorry for my ambiguious explaination, I just mean by some original code might be changed on your side which makes the difference.
that's pretty strange as I've also clone and run the code this morning and it shows correct result. Are you sure you follow the same step and with no code...
Hi, thank you for telling me that. Actually, this is not a "bug", but an implementation trick. We only estimated the bounding box of view 1, which is also the...
Hey, 'view' means camera view. Yes, the code only evaluate view 1, as this is the standard evaluation protocol.
no, it is bbx of view 1, preframe, corresponds to view1, 2, 3 bbx, which is wrong for view 2, 3, but works correctly on view1, which is the evaluation...
Thanks a lot for informing me about this. I'll update accordingly.
This idea is great. Actually I've tried with the similar idea, to use hand color to crop out hand. Unfortunately, rgb and d is not calibrated and well-aligned for the...
Hi, run_preprocess() in msra.py was used to check the TF record and has nothing to do with the whole pipeline. There's no need to run this function.
Hey. Thank you for your interest. Yes, the mask trick, together with we are also treating coordinate as input feature feed them to the network, are not mentioned in the...
for nyu dataset, we've trained another independent network for bounding box regression, but it is not part of the current project.