muses0229
muses0229
Here is my code to project points,the R,T,K are all cameras' parameters. RT = torch.cat([torch.tensor(data.R.transpose()), torch.tensor(data.T).reshape(3,1)], -1)[None, None].cuda() xyz = torch.repeat_interleave(world_3d_pts.squeeze(0)[None, None], repeats=RT.shape[1], dim=1) xyz = torch.matmul(RT[:, :, None, :,...
The result is still not right..., I'd like to know is R,T in smpl coordinate or world coordinate?
Here is the projected image I get now: 
sorry for bothering again,but my projection result still seems a bit wrong:  I'm pretty sure my projection code is right because I get the same result using your code....
I check my code and found I add wrong transpose on camera.R,now my projection result is like that:  Is this looks right now?
kaolin version:0.10.0 torch1.11.0+cu11.5
gpu:1080Ti
I have solve this problem,thank you so much. But when I validate the model using this script:python validate.py --novel-view --num-workers 4 ${path_to_config},I encounter CUDA out of memory,I am using a...
Is it because the memory was not cleaned during validating?