gushengbo

how to use thuman2.0 dataset

How to train humannerf with snap_shot?

11

I train humannerf with snap_shot, but produce empty image. Could you tell me how to train humannerf with snap_shot?

What other data sets humannerf can run besides ZJU_mocap？

4

Thank you very much!

question about setup error

3

kaolin/csrc/ops/conversions/mesh_to_spc/mesh_to_spc_cuda.cu:21:10: fatal error: cub/device/device_scan.cuh: No such file or directory #include ^~~~~~~~~~~~~~~~~~~~~~~~~~~~

Why can't I use the smplx downloaded from thuman2 github？

12

the smplx downloaded from thuman2 github can align with scans. but when I run test in thuman2, I get error.  I want to know have you dealed with the...

some error when run evaluation.md on thuman2

4

when I run python -m apps.train -cfg ./configs/train/icon-filter.yaml -test on thuman2, I get error:  but when I run on cape, that's right. 

[BUG] RuntimeError: CUDA error: initialization error

2

```bash File "/home/shengbo/ICON-master/lib/common/seg3d_lossless.py", line 169, in _forward_faster occupancys = self.batch_eval(coords, **kwargs) File "/home/shengbo/ICON-master/lib/common/seg3d_lossless.py", line 138, in batch_eval occupancys = self.query_func(**kwargs, points=coords2D) File "/home/shengbo/ICON-master/lib/common/train_util.py", line 434, in query_func preds = netG.query(features=features,...

Initializing distributed: GLOBAL_RANK: 1, MEMBER: 2/2 [INFO] ---------------------------------------------------------------------------------------------------- distributed_backend=nccl All distributed processes registered. Starting with 2 processes ---------------------------------------------------------------------------------------------------- [INFO] LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0,1] [INFO] LOCAL_RANK: 1 - CUDA_VISIBLE_DEVICES: [0,1]...

Is there any evaluation code?

2

Is there any evaluation code?