Onion1024
commented
2 months ago 直接下载main(Linux)那个分支的checkpoint链接，但是要注意文件下载不全的问题
Closed Onion1024 closed 2 months ago
Onion1024
commented
2 months ago 直接下载main(Linux)那个分支的checkpoint链接，但是要注意文件下载不全的问题
操作系统：windows11 64位 步骤：按照官方文档步骤操作 问题描述： 在anaconda环境下执行 bash run_test.sh 脚本时报错：
(wonder3d) PS D:\工作文件夹\3D建模\program\Wonder3D> bash .\run_test.sh A matching Triton is not available, some optimizations will not be enabled. Error caught was: No module named 'triton' {'pretrained_model_name_or_path': './ckpts', 'pretrained_unet_path': './ckpts/', 'revision': None, 'validation_dataset': {'root_dir': './example_images', 'num_views': 6, 'bg_color': 'white', 'img_wh': [256, 256], 'num_validation_samples': 1000, 'crop_size': 192, 'filepaths': ['owl.png']}, 'save_dir': 'outputs/', 'pred_type': 'joint', 'seed': 42, 'validation_batch_size': 1, 'dataloader_num_workers': 64, 'local_rank': -1, 'pipe_kwargs': {'camera_embedding_type': 'e_de_da_sincos', 'num_views': 6}, 'validation_guidance_scales': [3.0], 'pipe_validation_kwargs': {'eta': 1.0}, 'validation_grid_nrow': 6, 'unet_from_pretrained_kwargs': {'camera_embedding_type': 'e_de_da_sincos', 'projection_class_embeddings_input_dim': 10, 'num_views': 6, 'sample_size': 32, 'zero_init_conv_in': False, 'zero_init_camera_projection': False}, 'num_views': 6, 'camera_embedding_type': 'e_de_da_sincos', 'enable_xformers_memory_efficient_attention': True} Traceback (most recent call last): File "D:\工作文件夹\3D建模\program\Wonder3D\test_mvdiffusion_seq.py", line 335, in
main(cfg)
File "D:\工作文件夹\3D建模\program\Wonder3D\test_mvdiffusion_seq.py", line 251, in main
image_encoder = CLIPVisionModelWithProjection.from_pretrained(cfg.pretrained_model_name_or_path, subfolder="image_encoder", revision=cfg.revision)
File "D:\installed\anaconda3\envs\wonder3d\lib\site-packages\transformers\modeling_utils.py", line 3354, in from_pretrained
config, model_kwargs = cls.config_class.from_pretrained(
File "D:\installed\anaconda3\envs\wonder3d\lib\site-packages\transformers\models\clip\configuration_clip.py", line 246, in from_pretrained
config_dict, kwargs = cls.get_config_dict(pretrained_model_name_or_path, kwargs)
File "D:\installed\anaconda3\envs\wonder3d\lib\site-packages\transformers\configuration_utils.py", line 632, in get_config_dict
config_dict, kwargs = cls._get_config_dict(pretrained_model_name_or_path, kwargs)
File "D:\installed\anaconda3\envs\wonder3d\lib\site-packages\transformers\configuration_utils.py", line 689, in _get_config_dict
resolved_config_file = cached_file(
File "D:\installed\anaconda3\envs\wonder3d\lib\site-packages\transformers\utils\hub.py", line 373, in cached_file
raise EnvironmentError(
OSError: ./ckpts does not appear to have a file named image_encoder\config.json. Checkout 'https://huggingface.co/./ckpts/tree/None' for available files.
Traceback (most recent call last):
File "D:\installed\anaconda3\envs\wonder3d\lib\runpy.py", line 197, in _run_module_as_main
return _run_code(code, main_globals, None,
File "D:\installed\anaconda3\envs\wonder3d\lib\runpy.py", line 87, in _run_code
exec(code, run_globals)
File "D:\installed\anaconda3\envs\wonder3d\Scripts\accelerate.exe__main__.py", line 7, in
File "D:\installed\anaconda3\envs\wonder3d\lib\site-packages\accelerate\commands\accelerate_cli.py", line 48, in main
args.func(args)
File "D:\installed\anaconda3\envs\wonder3d\lib\site-packages\accelerate\commands\launch.py", line 1174, in launch_command
simple_launcher(args)
File "D:\installed\anaconda3\envs\wonder3d\lib\site-packages\accelerate\commands\launch.py", line 769, in simple_launcher
raise subprocess.CalledProcessError(returncode=process.returncode, cmd=cmd)
subprocess.CalledProcessError: Command '['D:\installed\anaconda3\envs\wonder3d\python.exe', 'test_mvdiffusion_seq.py', '--config', 'configs/mvdiffusion-joint-ortho-6views.yaml']' returned non-zero exit status 1.
提示没有triton模块，以及后续提到ckpts中缺少文件，导致后续脚本无法正确执行。
请问是否要安装triton模块？ckpts在OneDrive中的文件是否缺少？