I meet some bugs when [Panorama-to-3D]: python train.py -s data/alley_pano -m output/test

[Nicous20]

Traceback (most recent call last):
File "train.py", line 18, in
from gaussian_renderer import render, network_gui
File "/root/DreamScene360/gaussian_renderer/init.py", line 15, in
from scene.gaussian_model import GaussianModel
File "/root/DreamScene360/scene/init.py", line 19, in
from utils.camera_utils import cameraList_from_camInfos, camera_to_JSON, img_coord_to_pano_direction ###
File "/root/DreamScene360/utils/camera_utils.py", line 17, in
from utils.depth_utils import estimate_depth
File "/root/DreamScene360/utils/depth_utils.py", line 25, in
model.load_state_dict(state_dict)
File "/opt/conda/envs/dreamscene360/lib/python3.8/site-packages/torch/nn/modules/module.py", line 2215, in load_state_dict
raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format(
RuntimeError: Error(s) in loading state_dict for DPTDepthModel:
size mismatch for scratch.output_conv.4.weight: copying a param with shape torch.Size([3, 32, 1, 1]) from checkpoint, the shape in current model is torch.Size([1, 32, 1, 1]).
size mismatch for scratch.output_conv.4.bias: copying a param with shape torch.Size([3]) from checkpoint, the shape in current model is torch.Size([1]).