caitongbo
commented
4 months ago (talking_gaussian) ubuntu@tech-aigc-server:/app/dev/TalkingGaussian$ bash scripts/train_xx.sh
Optimizing output/wanghui0620
Output folder: output/wanghui0620 [07/07 16:46:10]
Found transforms_train.json file, assuming Blender data set! [07/07 16:46:11]
Reading Training Transforms [07/07 16:46:11]
1914it [00:00, 4252.13it/s]
0 32 [07/07 16:46:11]
1914it [00:27, 68.91it/s]
Reading Test Transforms [07/07 16:46:39]
192it [00:00, 4244.11it/s]
0 32 [07/07 16:46:39]
192it [00:02, 69.19it/s]
Generating random point cloud (10000)... [07/07 16:46:42]
Loading Training Cameras [07/07 16:46:42]
Loading Test Cameras [07/07 16:46:44]
Number of points at initialisation : 10000 [07/07 16:46:44]
Setting up [LPIPS] perceptual loss: trunk [alex], v[0.1], spatial [off] [07/07 16:46:44]
/home/ubuntu/miniconda3/envs/talking_gaussian/lib/python3.7/site-packages/torchvision/models/_utils.py:209: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and may be removed in the future, please use 'weights' instead.
f"The parameter '{pretrained_param}' is deprecated since 0.13 and may be removed in the future, "
/home/ubuntu/miniconda3/envs/talking_gaussian/lib/python3.7/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or None for 'weights' are deprecated since 0.13 and may be removed in the future. The current behavior is equivalent to passing weights=AlexNet_Weights.IMAGENET1K_V1. You can also use weights=AlexNet_Weights.DEFAULT to get the most up-to-date weights.
warnings.warn(msg)
Loading model from: /home/ubuntu/miniconda3/envs/talking_gaussian/lib/python3.7/site-packages/lpips/weights/v0.1/alex.pth [07/07 16:46:44]
Training progress: 0%| | 0/50000 [00:00<?, ?it/s]Traceback (most recent call last):
File "train_mouth.py", line 328, in
Fictionarry
Hello, I encountered this error when trying to execute bash scripts/train_xx.sh. Could you please advise on how to resolve it? Thank you!
Traceback (most recent call last): File "train_mouth.py", line 328, in
training(lp.extract(args), op.extract(args), pp.extract(args), args.test_iterations, args.save_iterations, args.checkpoint_iterations, args.start_checkpoint, args.debug_from)
File "train_mouth.py", line 139, in training
render_pkg = render(viewpoint_cam, gaussians, pipe, background)
File "/app/dev/TalkingGaussian/gaussian_renderer/init.py", line 94, in render
cov3D_precomp = cov3D_precomp)
ValueError: not enough values to unpack (expected 4, got 3)
Exception ignored in: <function tqdm.del at 0x7f3931f337a0>