ordinal-pose3d
ordinal-pose3d copied to clipboard
Code for "Ordinal Depth Supervision for 3D Human Pose Estimation", CVPR 2018
I downloaded the data provided from http://visiondata.cis.upenn.edu/ordinal/lsp-mpii/lsp-mpii-ordinal.zip. However, I found the joints annotation does not match the image. Does joints ordinates are scaled to 256x256? Thanks! ```python data_dir = "lsp-mpii-ordinal/mpii_upis1h"...
In order to confirm whether the hardware conditions of my laboratory are sufficient, I would like to ask how long does it take to complete the training of the network...
Hello! Have you check the evalH36M.m file, it has many bugs, like undefined values. And why the exp/ h36m/valid_*.h5 files amounts much more than the data/images?
Hi, Just want to check if I can work on windows and still use ordinal-pose3d. Thanks, Mritula
Hello,may I ask when will you update this repository with the training code?
hi I am very interested in section 3.3 of the paper,because i have the same problem,so,how to predict the score map. @geopavlakos
Hello, For the ordinal datasets provided in annot.mat and joints.mat scale and center of the people werenot given alongside would be great if you can provide them for both lsp...