Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

No such file or directory:cam103 #162

Open
mayBeYan opened this issue Jul 12, 2024 · 1 comment
Open

No such file or directory:cam103 #162

mayBeYan opened this issue Jul 12, 2024 · 1 comment

Comments

@mayBeYan
Copy link

Error information
PS D:\Project_3DGS\4DGaussians> python train.py -s data/multipleview/inputimage --port 6017 --expname "multipleview/inputimage" --configs arguments/multipleview/inputimage.py
2024-07-12 15:54:08.078370: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable TF_ENABLE_ONEDNN_OPTS=0.
2024-07-12 15:54:08.493721: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable TF_ENABLE_ONEDNN_OPTS=0.
Optimizing
Output folder: ./output/multipleview/inputimage [12/07 15:54:09]
feature_dim: 32 [12/07 15:54:09]
D:\Project_3DGS\4DGaussians\data\multipleview\inputimage\cam103\frame_00001.jpg [12/07 15:54:09]
Traceback (most recent call last):
File "D:\Project_3DGS\4DGaussians\train.py", line 429, in
training(lp.extract(args), hp.extract(args), op.extract(args), pp.extract(args), args.test_iterations, args.save_iterations, args.checkpoint_iterations, args.start_checkpoint, args.debug_from, args.expname)
File "D:\Project_3DGS\4DGaussians\train.py", line 303, in training
scene = Scene(dataset, gaussians, load_coarse=None)
File "D:\Project_3DGS\4DGaussians\scene_init_.py", line 62, in init
scene_info = sceneLoadTypeCallbacks"MultipleView"
File "D:\Project_3DGS\4DGaussians\scene\dataset_readers.py", line 605, in readMultipleViewinfos
test_cam_infos = multipleview_dataset(cam_extrinsics=cam_extrinsics, cam_intrinsics=cam_intrinsics, cam_folder=datadir,split="test")
File "D:\Project_3DGS\4DGaussians\scene\multipleview_dataset.py", line 30, in init
self.video_cam_infos=self.get_video_cam_infos(cam_folder)
File "D:\Project_3DGS\4DGaussians\scene\multipleview_dataset.py", line 72, in get_video_cam_infos
image = Image.open(self.image_paths[0])
File "D:\Anaconda\envs\S3Gaussian\lib\site-packages\PIL\Image.py", line 3431, in open
fp = builtins.open(filename, "rb")
FileNotFoundError: [Errno 2] No such file or directory: 'D:\Project_3DGS\4DGaussians\data\multipleview\inputimage\cam103\frame_00001.jpg'

Hi,i get a confuse problem about my custom multiview training , i get the error infomation like this.
However , i only have three cam as you can see in the picture , what this program want to get images in cam103 ,and how can i solve the problem ?
屏幕截图 2024-07-12 161317

@Hongyuan-Tao
Copy link

Have you correctly followed the readme document process to use colmap to calculate point clouds and poses?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants