Function _RasterizeGaussiansBackward returned an invalid gradient at index 2 - got [0, 0, 3] but expected shape compatible with [0, 16, 3]

[123456xuan]

Hi, thanks for the code you provided, I solved a lot of things in this code. However, the following problem occurred when I used my own D-bit data set. I checked many parts of the code that could be modified, but still couldn't find a solution, so please help me to answer this problem, thank you very much.

Traceback (most recent call last):
File "/home/root/FSGS/train.py", line 282, in
training(lp.extract(args), op.extract(args), pp.extract(args), args)
File "/home/root/FSGS/train.py", line 139, in training
loss.backward()
File "/opt/anaconda3/envs/3dgs/lib/python3.9/site-packages/torch/_tensor.py", line 522, in backward
torch.autograd.backward(
File "/opt/anaconda3/envs/3dgs/lib/python3.9/site-packages/torch/autograd/init.py", line 266, in backward
Variable._execution_engine.run_backward( # Calls into the C++ engine to run the backward pass
RuntimeError: Function _RasterizeGaussiansBackward returned an invalid gradient at index 2 - got [0, 0, 3] but expected shape compatible with [0, 16, 3]
Training progress: 0%| | 0/10000 [00:00<?, ?it/s]