kevinlin311tw
commented
2 years ago Sorry, we don't have the 64-frame step evaluation. We follow the evaluation protocol used in the literature. Specifically, we adopt evaluation code from Convolutional Mesh Regression for Single-Image Human Shape Reconstruction, CVPR 2019
Hi! I have a question about evaluation. human36m protocol2 execute on subject9,11 with 64 frame steps. but i think your code is on 5 frame steps. ex) _000001.jpg, _000006.jpg, _000011.jpg, ...
Could you share 64 frame steps evaluation code?