xxlong0 / Wonder3D

Single Image to 3D using Cross-Domain Diffusion for 3D Generation
https://www.xxlong.site/Wonder3D/
GNU Affero General Public License v3.0
4.83k stars 389 forks source link

TypeError: unsupported operand type(s) for //: 'int' and 'NoneType' #135

Open legendCaptain opened 10 months ago

legendCaptain commented 10 months ago

hi,I run gradio_app_recon.py, an error occurred: TypeError: unsupported operand type (s) for//: 'int' and 'NoneType'. Do you know how to handle it? Below is the error message: (wonder3d) root@autodl-container-b2fc4a9fb5-bd99e4b1:~/autodl-tmp/python_project/wonder3d# python gradio_app_recon.py Loading pipeline components...: 0%| | 0/5 [00:02<?, ?it/s] Traceback (most recent call last): File "gradio_app_recon.py", line 438, in fire.Fire(run_demo) File "/root/miniconda3/envs/wonder3d/lib/python3.8/site-packages/fire/core.py", line 141, in Fire component_trace = _Fire(component, args, parsed_flag_args, context, name) File "/root/miniconda3/envs/wonder3d/lib/python3.8/site-packages/fire/core.py", line 475, in _Fire component, remaining_args = _CallAndUpdateTrace( File "/root/miniconda3/envs/wonder3d/lib/python3.8/site-packages/fire/core.py", line 691, in _CallAndUpdateTrace component = fn(varargs, kwargs) File "gradio_app_recon.py", line 322, in run_demo pipeline = load_wonder3d_pipeline(cfg) File "gradio_app_recon.py", line 158, in load_wonder3d_pipeline pipeline = MVDiffusionImagePipeline.from_pretrained( File "/root/miniconda3/envs/wonder3d/lib/python3.8/site-packages/diffusers/pipelines/pipeline_utils.py", line 1069, in from_pretrained loaded_sub_model = load_sub_model( File "/root/miniconda3/envs/wonder3d/lib/python3.8/site-packages/diffusers/pipelines/pipeline_utils.py", line 471, in load_sub_model loaded_sub_model = load_method(cached_folder, loading_kwargs) File "/root/miniconda3/envs/wonder3d/lib/python3.8/site-packages/transformers/modeling_utils.py", line 3594, in from_pretrained model = cls(config, model_args, **model_kwargs) File "/root/miniconda3/envs/wonder3d/lib/python3.8/site-packages/transformers/models/clip/modeling_clip.py", line 1245, in init self.vision_model = CLIPVisionTransformer(config) File "/root/miniconda3/envs/wonder3d/lib/python3.8/site-packages/transformers/models/clip/modeling_clip.py", line 816, in init self.encoder = CLIPEncoder(config) File "/root/miniconda3/envs/wonder3d/lib/python3.8/site-packages/transformers/models/clip/modelingclip.py", line 567, in init self.layers = nn.ModuleList([CLIPEncoderLayer(config) for in range(config.num_hidden_layers)]) File "/root/miniconda3/envs/wonder3d/lib/python3.8/site-packages/transformers/models/clip/modelingclip.py", line 567, in self.layers = nn.ModuleList([CLIPEncoderLayer(config) for in range(config.num_hidden_layers)]) File "/root/miniconda3/envs/wonder3d/lib/python3.8/site-packages/transformers/models/clip/modeling_clip.py", line 347, in init self.self_attn = CLIPAttention(config) File "/root/miniconda3/envs/wonder3d/lib/python3.8/site-packages/transformers/models/clip/modeling_clip.py", line 232, in init self.head_dim = self.embed_dim // self.num_heads TypeError: unsupported operand type(s) for //: 'int' and 'NoneType'

legendCaptain commented 9 months ago

I figured out I had the wrong file in my ckpts