Dnerf dataset

[Haza628]

When training on the D-Nerf dataset, an error occurred at the 7500th iteration:

9%|████████████████▍ | 7499/80000 [10:22<1:40:13, 12.06it/s] Traceback (most recent call last): File "D:\Guo\code\GSTracking\Dynamic-2DGS\train_gui.py", line 671, in gui.train(args.iterations) File "D:\Guo\code\GSTracking\Dynamic-2DGS\train_gui.py", line 211, in train self.train_node_rendering_step() File "D:\Guo\code\GSTracking\Dynamic-2DGS\train_gui.py", line 569, in train_node_rendering_step hyper_pcl = (trans_samp + original_gaussians.get_xyz[:, None]).reshape([original_gaussians.get_xyz.shape[0], -1]) RuntimeError: cannot reshape tensor of 0 elements into shape [0, -1] because the unspecified dimension size -1 can be any value and is ambiguous

Do you know what caused this?

[Shuaizhang7]

There may be a problem with the reshape operation, check original_gaussians.get_xyz.shape[0] to see if it is 0?