Giters

Arthur151 / ROMP

Monocular, One-stage, Regression of Multiple 3D People and their 3D positions & trajectories in camera & global coordinates. ROMP[ICCV21], BEV[CVPR22], TRACE[CVPR2023]

Home Page:https://www.yusun.work/

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Issues with the post processing code

mkhoshle opened this issue · comments

commented

Hello,

I am training the code on 3DPW. I start from pre-trained resnet backbone and finetune the backbone during the training. During training the visualized results look pretty reasonable:
im3
im3_reconstruction
However when I save the model as a .pkl file and use it using test.py or image.py to do the prediction I get nothing. I am so confused, am I doing anything wrong here?
media_images_Heatmaps_32_a24a022ab65db3f35b5a

media_images_Mesh_Rensering_17_cb851c8455cacb661a49

I appreciate any feedback.
Thanks

commented

Hi, did you solved this problem?