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
Traceback (most recent call last):
File "/home/xxx/3DGS/CF-3DGS/run_cf3dgs.py", line 47, in
trainer.train_from_progressive()
File "/home/xxx/3DGS/CF-3DGS/trainer/cf3dgs_trainer.py", line 445, in train_from_progressive
gauss_params = self.init_two_view(
File "/home/xxx/3DGS/CF-3DGS/trainer/cf3dgs_trainer.py", line 198, in init_two_view
loss, rend_dict, psnr_train = self.train_step(self.gs_render,
File "/home/xxx/3DGS/CF-3DGS/trainer/cf3dgs_trainer.py", line 119, in train_step
image, viewspace_point_tensor, visibility_filter, radii = (render_pkg["image"],
TypeError: 'NoneType' object is not subscriptable
Training progress: 0%|
solution:
in file gaussian_model_cf.py
in the end ,add this:
elif len(out) == 5:
rendered_image, radii, rendered_depth, rendered_alpha, n_touched= out
rendered_image = rendered_image.clamp(0, 1)
# Those Gaussians that were frustum culled or had a radius of 0 were not visible.
# They will be excluded from value updates used in the splitting criteria.
return {
"image": rendered_image,
"depth": rendered_depth,
"viewspace_points": screenspace_points,
"visibility_filter": radii > 0,
"radii": radii,
"n_touched": n_touched,
}
The text was updated successfully, but these errors were encountered:
Traceback (most recent call last):
File "/home/xxx/3DGS/CF-3DGS/run_cf3dgs.py", line 47, in
trainer.train_from_progressive()
File "/home/xxx/3DGS/CF-3DGS/trainer/cf3dgs_trainer.py", line 445, in train_from_progressive
gauss_params = self.init_two_view(
File "/home/xxx/3DGS/CF-3DGS/trainer/cf3dgs_trainer.py", line 198, in init_two_view
loss, rend_dict, psnr_train = self.train_step(self.gs_render,
File "/home/xxx/3DGS/CF-3DGS/trainer/cf3dgs_trainer.py", line 119, in train_step
image, viewspace_point_tensor, visibility_filter, radii = (render_pkg["image"],
TypeError: 'NoneType' object is not subscriptable
Training progress: 0%|
solution:
in file gaussian_model_cf.py
in the end ,add this:
The text was updated successfully, but these errors were encountered: