vvanurag
commented
10 months ago I solved this by rebuilding extensions 'bash scripts/install_ext.sh'. I previously downgraded dearpygui to match GLIBC2.28. We need to reinstall extensions if they have to run correctly.
I ran the simulate.py over stonehenge dataset. I got the following error.
/home/vvisagak/.conda/envs/nerfnav/lib/python3.11/site-packages/torch/functional.py:504: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at /opt/conda/conda-bld/pytorch_1682343995622/work/aten/src/ATen/native/TensorShape.cpp:3483.) return _VF.meshgrid(tensors, kwargs) # type: ignore[attr-defined] Traceback (most recent call last): File "/home/vvisagak/nerf_ws/nerf-navigation/simulate.py", line 350, in
simulate(planner_cfg, agent_cfg, filter_cfg, extra_cfg, density_fn, render_fn, get_rays_fn)
File "/home/vvisagak/nerf_ws/nerf-navigation/simulate.py", line 46, in simulate
traj.a_star_init()
File "/home/vvisagak/nerf_ws/nerf-navigation/nav/quad_plot.py", line 79, in a_star_init
output = self.nerf(coods)
^^^^^^^^^^^^^^^^
File "/home/vvisagak/nerf_ws/nerf-navigation/simulate.py", line 343, in
density_fn = lambda x: model.density(x.reshape((-1, 3)) @ rot)['sigma'].reshape(x.shape[:-1])
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/vvisagak/nerf_ws/nerf-navigation/nerf/network.py", line 129, in density
x = self.encoder(x, bound=self.bound)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/vvisagak/.conda/envs/nerfnav/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, *kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/vvisagak/nerf_ws/nerf-navigation/gridencoder/grid.py", line 151, in forward
outputs = grid_encode(inputs, self.embeddings, self.offsets, self.per_level_scale, self.base_resolution, inputs.requires_grad, self.gridtype_id, self.align_corners)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/vvisagak/.conda/envs/nerfnav/lib/python3.11/site-packages/torch/autograd/function.py", line 506, in apply
return super().apply(args, kwargs) # type: ignore[misc]
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/vvisagak/.conda/envs/nerfnav/lib/python3.11/site-packages/torch/cuda/amp/autocast_mode.py", line 98, in decorate_fwd
return fwd(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^
File "/home/vvisagak/nerf_ws/nerf-navigation/gridencoder/grid.py", line 49, in forward
_backend.grid_encode_forward(inputs, embeddings, offsets, outputs, B, D, C, L, S, H, calc_grad_inputs, dy_dx, gridtype, align_corners)
TypeError: grid_encode_forward(): incompatible function arguments. The following argument types are supported:
Invoked with: tensor([[0.2500, 0.2500, 0.2500], [0.2500, 0.2551, 0.2500], [0.2500, 0.2601, 0.2500], ..., [0.7500, 0.7399, 0.7500], [0.7500, 0.7449, 0.7500], [0.7500, 0.7500, 0.7500]]), Parameter containing: tensor([[-2.0191e-05, 3.3358e-06], [-9.5014e-05, 8.8016e-05], [ 8.9171e-05, 5.9346e-05], ..., [ 9.7341e-05, 2.5009e-06], [-9.2044e-05, -8.3519e-05], [ 1.6254e-05, -6.3481e-05]], requires_grad=True), tensor([ 0, 4920, 20552, 63432, 188432, 561680, 1085968, 1610256, 2134544, 2658832, 3183120, 3707408, 4231696, 4755984, 5280272, 5804560, 6328848], dtype=torch.int32), tensor([[[0., 0.], [0., 0.], [0., 0.], ..., [0., 0.], [0., 0.], [0., 0.]],