Open hariharanConstructn opened 3 months ago
Hi @hariharanConstructn! Have you recompiled the CUDA rasterizer following the readme by doing the following?
cd submodules/diff-gaussian-rasterization
pip install .
I solve this problem by using python3.8.
First of All Thank you for your wonderful work
:~/workdir/feature-3dgs$ python train.py -s data/TEST_DATA/ -m data/TEST_DATA/ -f sam --speedup Optimizing data/TEST_DATA/ Output folder: data/TEST_DATA/ [29/04 14:02:57] Reading camera 1622/1622 [29/04 14:03:02] Loading Training Cameras [29/04 14:03:02] Loading Test Cameras [29/04 14:03:24] Number of points at initialisation : 138708 [29/04 14:03:24] Training progress: 0%| | 0/30000 [00:00<?, ?it/s]Traceback (most recent call last): File "train.py", line 257, 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.py", line 105, in training
render_pkg = render(viewpoint_cam, gaussians, pipe, background)
File "/home/ubuntu/workdir/feature-3dgs/gaussian_renderer/init.py", line 250, in render
cov3D_precomp = cov3D_precomp)
File "/home/ubuntu/conda/envs/gaussian_splatting/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl
return forward_call(*input, **kwargs)
TypeError: forward() got an unexpected keyword argument 'semantic_feature'
Training progress: 0%| | 0/30000 [00:00<?, ?it/s](
After SAM ran, I try to train my model and I'm getting this error
" TypeError: forward() got an unexpected keyword argument 'semantic_feature' "