fanglinpu
fanglinpu
Thank you for your answer.
I am a little bit confused about the depth normalization processing, why is the hand depth values range from com[2]-D_RANDGE to com[2]+D_RANGE*0.5? The corresponding code is as follows: ``` def...
For ICVL and MSRA datasets, the cropped image from testing set is also obtained by exploiting the ground truth pose, I think it is inappropriate.
I use the learning rate 0.001, but the refined_loss_1 is nan.
Got it, thanks!