【已解决】RuntimeError: unexpected EOF, expected 884108 more bytes. The file might be corrupted.

这个是因为下载的模型文件损坏了，因为我这个只有modle.pt，所以肯定是这个文件有损坏，这个时候只要重新下载就可以了。

文章共1,427字 · 阅读需要大约5分钟

一键AI生成摘要，助你高效阅读

问答

鳗小鱼

1781人浏览 · 2023-12-07 00:01:35

鳗小鱼 · 2023-12-07 00:01:35 发布

问题描述

Traceback (most recent call last):
File "mist_v3.py", line 342, in <module>
config = init(epsilon=epsilon, steps=steps, mode=mode, rate=rate)
File "mist_v3.py", line 184, in init
model = load_model_from_config(config, ckpt_path).to(device)
File "mist_v3.py", line 53, in load_model_from_config
model = instantiate_from_config(config.model)
File "/media/visionx/monica/project/modelwatermark/mist/ldm/util.py", line 85, in instantiate_from_config
return get_obj_from_str(config["target"])(**config.get("params", dict()))
File "/media/visionx/monica/project/modelwatermark/mist/ldm/models/diffusion/ddpmAttack.py", line 460, in __init__
self.instantiate_cond_stage(cond_stage_config)
File "/media/visionx/monica/project/modelwatermark/mist/ldm/models/diffusion/ddpmAttack.py", line 518, in instantiate_cond_stage
model = instantiate_from_config(config)
File "/media/visionx/monica/project/modelwatermark/mist/ldm/util.py", line 85, in instantiate_from_config
return get_obj_from_str(config["target"])(**config.get("params", dict()))
File "/media/visionx/monica/project/modelwatermark/mist/ldm/util.py", line 93, in get_obj_from_str
return getattr(importlib.import_module(module, package=None), cls)
File "/home/visionx/anaconda3/envs/mist/lib/python3.8/importlib/__init__.py", line 127, in import_module
return _bootstrap._gcd_import(name[level:], package, level)
File "<frozen importlib._bootstrap>", line 1014, in _gcd_import
File "<frozen importlib._bootstrap>", line 991, in _find_and_load
File "<frozen importlib._bootstrap>", line 975, in _find_and_load_unlocked
File "<frozen importlib._bootstrap>", line 671, in _load_unlocked
File "<frozen importlib._bootstrap_external>", line 783, in exec_module
File "<frozen importlib._bootstrap>", line 219, in _call_with_frames_removed
File "/media/visionx/monica/project/modelwatermark/mist/ldm/modules/encoders/modules.py", line 7, in <module>
import kornia
File "/home/visionx/anaconda3/envs/mist/lib/python3.8/site-packages/kornia/__init__.py", line 10, in <module>
from . import (
File "/home/visionx/anaconda3/envs/mist/lib/python3.8/site-packages/kornia/augmentation/__init__.py", line 43, in <module>
from .container import AugmentationSequential, ImageSequential, PatchSequential, VideoSequential
File "/home/visionx/anaconda3/envs/mist/lib/python3.8/site-packages/kornia/augmentation/container/__init__.py", line 1, in <module>
from .augment import AugmentationSequential
File "/home/visionx/anaconda3/envs/mist/lib/python3.8/site-packages/kornia/augmentation/container/augment.py", line 17, in <module>
from .patch import PatchSequential
File "/home/visionx/anaconda3/envs/mist/lib/python3.8/site-packages/kornia/augmentation/container/patch.py", line 9, in <module>
from kornia.contrib.extract_patches import extract_tensor_patches
File "/home/visionx/anaconda3/envs/mist/lib/python3.8/site-packages/kornia/contrib/__init__.py", line 4, in <module>
from .image_stitching import ImageStitcher
File "/home/visionx/anaconda3/envs/mist/lib/python3.8/site-packages/kornia/contrib/image_stitching.py", line 7, in <module>
from kornia.feature import LocalFeatureMatcher, LoFTR
File "/home/visionx/anaconda3/envs/mist/lib/python3.8/site-packages/kornia/feature/__init__.py", line 4, in <module>
from .integrated import (
File "/home/visionx/anaconda3/envs/mist/lib/python3.8/site-packages/kornia/feature/integrated.py", line 52, in <module>
class LAFDescriptor(nn.Module):
File "/home/visionx/anaconda3/envs/mist/lib/python3.8/site-packages/kornia/feature/integrated.py", line 65, in LAFDescriptor
patch_descriptor_module: nn.Module = HardNet(True),
File "/home/visionx/anaconda3/envs/mist/lib/python3.8/site-packages/kornia/feature/hardnet.py", line 66, in __init__
pretrained_dict = torch.hub.load_state_dict_from_url(
File "/home/visionx/anaconda3/envs/mist/lib/python3.8/site-packages/torch/hub.py", line 595, in load_state_dict_from_url
return torch.load(cached_file, map_location=map_location)
File "/home/visionx/anaconda3/envs/mist/lib/python3.8/site-packages/torch/serialization.py", line 713, in load
return _legacy_load(opened_file, map_location, pickle_module, **pickle_load_args)
File "/home/visionx/anaconda3/envs/mist/lib/python3.8/site-packages/torch/serialization.py", line 938, in _legacy_load
typed_storage._storage._set_from_file(
RuntimeError: unexpected EOF, expected 884108 more bytes. The file might be corrupted.

问题解决

这个是因为下载的模型文件损坏了，因为我这个只有modle.pt，所以肯定是这个文件有损坏，这个时候只要重新下载就可以了

wget -c https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt

延伸阅读

问题一：预训练权重文件损坏

在使用深度学习训练时，运行trian.py文件，代码会自动连网下载预训练权重文件，由于权重文件一般在外网，网络不稳定，下载速度特别慢，下载失败后再次运行train.py文件就会提示出错，错误如下：RuntimeError: unexpected EOF, expected 441443 more bytes. The file might be corrupted出现这种情况的主要原因是第一次运行代码下载了部分预训练权重文件，因网络不稳定等原因中断了，就导致下载的权重文件损坏了，如果想重新下载，就必须删除最开始下载的损坏权重文件。那最开始下载的权重文件被自动保存到了哪个路径下呢？我们要注意第一次下载权重文件时的提示，会告诉你它保存到了哪个路径下