Issues in PytochNerfactoField

[shuimoo]

when using PytochNerfactoField instead of TCNNNerfactoField, some problems came out.

File "/root/qnerf/nerfstudio/fields/nerfacto_field.py", line 347, in get_density
    encoded_xyz = self.position_encoding(positions)
  File "/root/anaconda3/envs/nerfstudio/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl
    return forward_call(*input, **kwargs)
  File "/root/qnerf/nerfstudio/field_components/encodings.py", line 342, in forward
    return self.tcnn_encoding(in_tensor)
  File "/root/anaconda3/envs/nerfstudio/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl
    return forward_call(*input, **kwargs)
  File "/root/anaconda3/envs/nerfstudio/lib/python3.8/site-packages/tinycudann/modules.py", line 145, in forward
    output = _module_function.apply(
  File "/root/anaconda3/envs/nerfstudio/lib/python3.8/site-packages/tinycudann/modules.py", line 57, in forward
    native_ctx, output = native_tcnn_module.fwd(input, params)
RuntimeError: /tiny-cuda-nn/bindings/torch/tinycudann/bindings.cpp:88 check failed input.size(1) == n_input_dims()