opendatalab / PDF-Extract-Kit

A Comprehensive Toolkit for High-Quality PDF Content Extraction
GNU Affero General Public License v3.0
4.72k stars 319 forks source link

_pickle.UnpicklingError: invalid load key, 'v'. 错误 #90

Open 724852499 opened 1 month ago

724852499 commented 1 month ago

root@ca9782e90bf9:/home/pdf/PDF-Extract-Kit# python pdf_extract.py --pdf /home/pdf/test.pdf Namespace(pdf='/home/pdf/test.pdf', output='output', vis=False, render=False) 2024-08-15 17:08:10 Started! Traceback (most recent call last): File "/home/pdf/PDF-Extract-Kit/pdf_extract.py", line 98, in mfd_model = mfd_model_init(model_configs['model_args']['mfd_weight']) File "/home/pdf/PDF-Extract-Kit/pdf_extract.py", line 31, in mfd_model_init mfd_model = YOLO(weight) File "/usr/local/lib/python3.10/site-packages/ultralytics/models/yolo/model.py", line 23, in init super().init(model=model, task=task, verbose=verbose) File "/usr/local/lib/python3.10/site-packages/ultralytics/engine/model.py", line 142, in init self._load(model, task=task) File "/usr/local/lib/python3.10/site-packages/ultralytics/engine/model.py", line 294, in _load self.model, self.ckpt = attempt_load_one_weight(weights) File "/usr/local/lib/python3.10/site-packages/ultralytics/nn/tasks.py", line 855, in attempt_load_one_weight ckpt, weight = torch_safe_load(weight) # load ckpt File "/usr/local/lib/python3.10/site-packages/ultralytics/nn/tasks.py", line 781, in torch_safe_load ckpt = torch.load(file, map_location="cpu") File "/usr/local/lib/python3.10/site-packages/ultralytics/utils/patches.py", line 86, in torch_load return _torch_load(*args, kwargs) File "/usr/local/lib/python3.10/site-packages/torch/serialization.py", line 1040, in load return _legacy_load(opened_file, map_location, pickle_module, pickle_load_args) File "/usr/local/lib/python3.10/site-packages/torch/serialization.py", line 1262, in _legacy_load magic_number = pickle_module.load(f, **pickle_load_args) _pickle.UnpicklingError: invalid load key, 'v'. 执行命令报错,什么原因呢

myhloli commented 1 month ago

模型下载不完整,请检查模型文件大小和网页上是否一致,如果大小一致,可以进一步通过sha256确认是否下载完整。

724852499 commented 1 month ago

重新删除 下载还是有这个问题,能告知是哪个模型出错呢

myhloli commented 1 month ago

重新删除 下载还是有这个问题,能告知是哪个模型出错呢

通过文件大小比对一下呢?大小不一致的就是有问题的

724852499 commented 1 month ago

image

myhloli commented 1 month ago

image

大小太小了,确认下自己是不是没安装git lfs

724852499 commented 1 month ago

可以下载了,下载下来有点大啊,磁盘都装不下了,模型有多大呢,是必须全不下载还是可以选择一部分模型呢

myhloli commented 1 month ago

约6GB,需要全部下载

724852499 commented 1 month ago

image image 模型下载下来了,但提取这个错呢,是下载的模型有问题呢?

ouyanglinke commented 3 weeks ago

你看看你下载的这个模型多大,可能没下载完整

724852499 commented 3 weeks ago

下完整了,后面发现是内存不够加载模型报的错误信息

724852499 commented 3 weeks ago

如果只想使用cpu,不使用gpu,需要怎么操作呢

myhloli commented 3 weeks ago

如果只想使用cpu,不使用gpu,需要怎么操作呢

参考这个文档:https://github.com/opendatalab/PDF-Extract-Kit/blob/main/docs/Install_in_Windows_zh_cn.md#3修改config-使用cpu推理 修改两个地方的cuda为cpu

724852499 commented 3 weeks ago

好的,十分感谢