melonwan
melonwan
Hi, the bounding box is computed by a hand detector, which is based on a 2D hour-glass estimation.
this part is not included but is very simple to implement. You could also use the deep prior++ method which gives more accurate result according to my previous experiment. The...
thank you too for the valuble suggestions. I'll later clean the code again. Sorry for the inconvenience brought by.
Hi, this is a reservation file of GPU on server and depends on your specific configuration. Probably you don't need it.
thanks a lot for pointing this out. Actually we've only used first view for training. See as another part of the code in dataset.py/nyu line 64, where only first 1/3...
these are just some trial and error hacky stuffs.
msra provides bbx as starting point. It is very easy to crop out hand from icvl with heuristics, eg depth thresholding.
Unfortunately, this project only supports depth map input.
Sorry for my late reply. There's no need to uncomment last two functions, they are just used for checking the tf record.
Hi, I've downloaded the code and model, run again and the result is as expected. According to the tensorboard visualization, there could be something wrong with the preprocessing step, and...