Closed MrCri5py closed 4 years ago
Hello @MrCri5py, thank you for your interest in our work! Please visit our Custom Training Tutorial to get started, and see our Jupyter Notebook , Docker Image, and Google Cloud Quickstart Guide for example environments.
If this is a bug report, please provide screenshots and minimum viable code to reproduce your issue, otherwise we can not help you.
If this is a custom model or data training question, please note that Ultralytics does not provide free personal support. As a leader in vision ML and AI, we do offer professional consulting, from simple expert advice up to delivery of fully customized, end-to-end production solutions for our clients, such as:
For more information please visit https://www.ultralytics.com.
In your PyInstaller .spec file, try adding caffe2_detectron_ops_gpu.dll to the binaries.
Example: binaries=[('path\to\your\caffe2_detectron_ops_gpu.dll' , '.')]
Note: If you use a conda environment the path should be similar to: [ANACONDA_ROOT]\envs\[ENV_NAME]\Lib\site-packages\torch\lib\caffe2_detectron_ops_gpu.dll
Thank you for your response @WelkinU . I have added the .DLL path to the binary and still gives the same issue. I've added --paths "path containing the .DLL", this then changed the error to PyInstallerImportError: Failed to load dynlib/dll "caffe2_nvrtc.dll" Using Windows 10 build 18363.959 Anaconda Pyinstaller 3.6 Torchvision 0.2.2. Post 3 Pytorch 1.5.1 Cuda 10.2 Cuda toolkit 10.1.243
This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.
@WelkinU ๋ต๋ณ ๊ฐ์ฌํฉ๋๋ค . ๋ฐ์ด๋๋ฆฌ์ .DLL ๊ฒฝ๋ก๋ฅผ ์ถ๊ฐํ์ง๋ง ์ฌ์ ํ ๋์ผํ ๋ฌธ์ ๊ฐ ๋ฐ์ํฉ๋๋ค. --paths "path ํฌํจ .DLL"์ ์ถ๊ฐํ๋ฉด PyInstallerImportError: Failed to load dynlib/dll "caffe2_nvrtc.dll" Using Windows 10 build 18363.959 Anaconda Pyinstaller 3.6 Torchvision 0.2.2. Post 3 Pytorch 1.5.1 Cuda 10.2 Cuda ํดํท 10.1.243
I've met he error too. How to solve?
โQuestion
I hope you are well.
I've got a question about creating an executable using YOLOv5. How do we go about to convert the detect. py script to an .exe? I have tried using Pyinstaller and cx_Freeze but this gives PyInstallerImportError: Failed to load dynlib/dll "caffe2_detectron_ops_gpu.dll". Your feedback will be highly appreciated. Thank you
Kind regards
Additional context