ZY Qin
ZY Qin
mkusner/wmd#18 you have to modify some lines in "python-emd-master\emd.h" (for python) or "emd\emd.h" (for matlab ) find definitions and edit MAX_SIG_SIZE #define MAX_SIG_SIZE 100 change 100 to bigger number (actually,...
For nan, you may try decreasing batch size.
The pretrained model's results are much better: - MPJPE: 10.01 mm - PA MPJPE: 4.52 mm You can get my train_logs.txt through this link: https://drive.google.com/file/d/1c_2qpufOuWGM_KmljYQpiXOm2em2iDZx/view?usp=sharing
Thank you :-) Let me give a try.
Same here. You need to change a lot of source files of TF.
Can you give an expected timeframe on when depth estimation will be available?
I am not very sure about this error. Maybe try decreasing the batch size a little bit?
@Zjz999hbq Have you figured out? I got stuck as well
I encountered the same issue. You need to adjust batch_size and batch_size_per_device, ensuring that the gradient accumulation is 4.