You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
when I "python train.py -s data/ggbond -m output/ggbond --data_device cpu", the trouble is turn up.
data/ggbond is only 160 MB.
my cuda is 11.8.
torch is :
python
Python 3.7.1 (default, Oct 28 2018, 08:39:03) [MSC v.1912 64 bit (AMD64)] :: Anaconda, Inc. on win32
Type "help", "copyright", "credits" or "license" for more information.
>>> import torch
>>> print(torch.cuda.is_available())
True
>>> print(torch.cuda.device_count())
1
>>> print(torch.version.cuda)
11.1
trouble:
python train.py -s data/ggbond -m output/ggbond --data_device cpu
Optimizing output/ggbond
Output folder: output/ggbond [20/01 11:39:18]
Tensorboard not available: not logging progress [20/01 11:39:18]
Reading camera 92/92 [20/01 11:39:18]
Loading Training Cameras [20/01 11:39:18]
[ INFO ] Encountered quite large input images (>1.6K pixels width), rescaling to 1.6K.
If this is not desired, please explicitly specify '--resolution/-r' as 1 [20/01 11:39:18]
Traceback (most recent call last):
File "train.py", line 277, in <module>
training(lp.extract(args), op.extract(args), pp.extract(args), args.test_iterations, args.save_iterations, args.checkpoint_iterations, args.start_checkpoint)
File "train.py", line 35, in training
scene = Scene(dataset, gaussians)
File "E:\workspace\2d-gaussian-splatting\scene\__init__.py", line 73, in __init__
self.train_cameras[resolution_scale] = cameraList_from_camInfos(scene_info.train_cameras, resolution_scale, args)
File "E:\workspace\2d-gaussian-splatting\utils\camera_utils.py", line 60, in cameraList_from_camInfos
camera_list.append(loadCam(args, id, c, resolution_scale))
File "E:\workspace\2d-gaussian-splatting\utils\camera_utils.py", line 54, in loadCam
image_name=cam_info.image_name, uid=id, data_device=args.data_device)
File "E:\workspace\2d-gaussian-splatting\scene\cameras.py", line 59, in __init__
self.camera_center = self.world_view_transform.inverse()[3, :3]
RuntimeError: cusolver error: 7, when calling `cusolverDnCreate(handle)`
The text was updated successfully, but these errors were encountered:
when I "python train.py -s data/ggbond -m output/ggbond --data_device cpu", the trouble is turn up.
data/ggbond is only 160 MB.
my cuda is 11.8.
torch is :
python
trouble:
The text was updated successfully, but these errors were encountered: