Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

ImportError: DLL load failed while importing _nncase #451

Closed
lanhaosmile opened this issue Nov 24, 2021 · 2 comments
Closed

ImportError: DLL load failed while importing _nncase #451

lanhaosmile opened this issue Nov 24, 2021 · 2 comments

Comments

@lanhaosmile
Copy link

Describe the bug
用nncase将onnx的模型转kmodel,运行转换脚本后提示:

Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
ImportError: DLL load failed while importing _nncase: 找不到指定的模块。

To Reproduce

import nncase

Expected behavior

Origin model and code
C:\Users\xxx\AppData\Local\Programs\Python\Python39\Lib\site-packages\nncase\base.py

import os
import sys


os.environ['KMP_DUPLICATE_LIB_OK'] = 'True'
import _nncase

Environment (please complete the following information):

  • OS: [Windows10]
  • nncase version [v1.0.0.20211029]

Additional context

  • 通过nncase-1.0.0.20211029-cp39-cp39-win_amd64.whl安装

  • pip list as belows:

Package Version
backports.entry-points-selectable 1.1.1
distlib 0.3.3
filelock 3.4.0
flatbuffers 2.0
nncase 1.0.0.20211029
numpy 1.21.4
onnx 1.10.2
onnx-simplifier 0.0.0
onnxoptimizer 0.2.6
onnxruntime 1.9.0
pip 20.2.3
platformdirs 2.4.0
protobuf 4.0.0rc2
setuptools 49.2.1
six 1.16.0
typing-extensions 4.0.0
virtualenv 20.10.0
virtualenvwrapper-win 1.2.6

@sunnycase
Copy link
Member

Please unzip and install libomp140.x86_64.zip to your system32 dir.

@sunnycase sunnycase pinned this issue Nov 24, 2021
@lanhaosmile
Copy link
Author

Please unzip and install libomp140.x86_64.zip to your system32 dir.

thanks a lot!

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants