Stage 1 training failed

[Ethan-Zhu-code]

Hi, thanks you for sharing your great work.

I am training on custom dataset following the command line with the exact same parameters: python main.py data/custom/ --workspace trial_custom -O --data_format colmap --bound 4 --scale 0.3 --stage 0 --clean_min_f 16 --clean_min_d 10 --lambda_tv 2e-8 --visibility_mask_dilation 50

After the stage 0 training finished, I got two meshes: mesh_0.ply and mesh_1.ply. Then I used the second command line to train for stage 1： python main.py data/custom/ --workspace trial_custom -O --data_format colmap --bound 4 --scale 0.3 --stage 1 --iters 10000 --lambda_normal 1e-3

However, exception occurred while the nerfrenderer try reading cascade meshes, which is shown as below: Traceback (most recent call last): File "/media/ethan/Files/nerf2mesh/main.py", line 159, in <module> model = NeRFNetwork(opt) File "/media/ethan/Files/nerf2mesh/nerf/network.py", line 38, in __init__ super().__init__(opt) File "/media/ethan/Files/nerf2mesh/nerf/renderer.py", line 121, in __init__ mesh = trimesh.load(os.path.join(self.opt.workspace, 'mesh_stage0', f'mesh_{cas}.ply'), force='mesh', skip_material=True, process=False) File "/home/ethan/anaconda3/envs/nerf2mesh/lib/python3.9/site-packages/trimesh/exchange/load.py", line 116, in load ) = parse_file_args(file_obj=file_obj, File "/home/ethan/anaconda3/envs/nerf2mesh/lib/python3.9/site-packages/trimesh/exchange/load.py", line 630, in parse_file_args raise ValueError('string is not a file: {}'.format(file_obj)) ValueError: string is not a file: trial_custom/mesh_stage0/mesh_2.ply

It seems the number of meshes the nerfrenderer tries to read is related to --bound, is it something wrong with my training data, or should I change the parameter for stage 1 training?