modelscope / richdreamer

Live Demo:https://modelscope.cn/studios/Damo_XR_Lab/3D_AIGC
https://aigc3d.github.io/richdreamer/
Apache License 2.0
362 stars 13 forks source link

Error when running nerf training #38

Closed yejr0229 closed 1 month ago

yejr0229 commented 1 month ago

Thanks for your great work! I run this command: "python3 ./run_nerf.py -t 'a penguin with husky dog costume' -o nerf_outputs/a_penguin_with_husky_dog_costume", and I have complete training, and I meet: [INFO] Initializing geometry from a given checkpoint ... Traceback (most recent call last): File "/public/omniteam/yejr/richdreamer-main/launch.py", line 237, in main(args, extras) File "/public/omniteam/yejr/richdreamer-main/launch.py", line 104, in main system: BaseSystem = threestudio.find(cfg.system_type)( File "/public/omniteam/yejr/richdreamer-main/threestudio/systems/base.py", line 41, in init self.configure() File "/public/omniteam/yejr/richdreamer-main/threestudio/systems/nd_mvdream.py", line 26, in configure super().configure() File "/public/omniteam/yejr/richdreamer-main/threestudio/systems/base.py", line 288, in configure self.geometry = threestudio.find(self.cfg.geometry_type).create_from( File "/public/omniteam/yejr/conda_env/richdreamer/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context return func(args, kwargs) File "/public/omniteam/yejr/richdreamer-main/threestudio/models/geometry/tetrahedra_sdf_grid.py", line 299, in create_from instance = TetrahedraSDFGrid(cfg, kwargs) File "/public/omniteam/yejr/richdreamer-main/threestudio/utils/base.py", line 101, in init self.configure(args, **kwargs) File "/public/omniteam/yejr/richdreamer-main/threestudio/models/geometry/tetrahedra_sdf_grid.py", line 73, in configure self.isosurface_helper = MarchingTetrahedraHelper( File "/public/omniteam/yejr/richdreamer-main/threestudio/models/isosurface.py", line 125, in init "indices", torch.from_numpy(tets["indices"]).long(), persistent=False File "/public/omniteam/yejr/conda_env/richdreamer/lib/python3.10/site-packages/numpy/lib/npyio.py", line 243, in getitem return format.read_array(bytes, File "/public/omniteam/yejr/conda_env/richdreamer/lib/python3.10/site-packages/numpy/lib/format.py", line 778, in read_array data = _read_bytes(fp, read_size, "array data") File "/public/omniteam/yejr/conda_env/richdreamer/lib/python3.10/site-packages/numpy/lib/format.py", line 907, in _read_bytes r = fp.read(size - len(data)) File "/public/omniteam/yejr/conda_env/richdreamer/lib/python3.10/zipfile.py", line 929, in read data = self._read1(n) File "/public/omniteam/yejr/conda_env/richdreamer/lib/python3.10/zipfile.py", line 1005, in _read1 data = self._decompressor.decompress(data, n) zlib.error: Error -3 while decompressing data: too many length or distance symbols time cost:1486.3226387500763

Is it a zip error? how to deal with it?

lingtengqiu commented 1 month ago

what is your python environment?

yejr0229 commented 1 month ago

it's python 3.10.14. can I just use another version of zip and not change the python version? it's really troublesome to recreate the environment...

lingtengqiu commented 1 month ago

please consider use conda to manage your python environment. The error is cased by wrong python environment.

yejr0229 commented 1 month ago

So what's the proper version of python?

yejr0229 commented 1 month ago

Please let me know your python version, thanks so much.