Skip to content

Conversation

hdnh2006
Copy link
Contributor

If dnn module with GPU support for openCV is available, the labeling will be done into the GPU.

You must install your dnn module with GPU support following by running the file opencv_dnn.sh.

This file is based on the instructions provided by Adrian Rosebrock (@jrosebr1) and he has the whole credit and not me.

TODO List

  • [] Support for Segment Anything
  • [] Custom yolov5 model
  • [] Yolov8 support

opencv_dnn.sh Outdated
Copy link
Owner

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think this file is not necessary because it cannot cover well on different machines.
Please remove this file. We will create a documentation site in the future for installation guide.

opencv_dnn.sh Outdated


# ln -s command is used to create a symbolic link, also known as a symlink or soft link
cd ~/.virtualenvs/opencv_cuda/lib/python3.8/site-packages/
Copy link
Owner

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Maybe other users do not have ~/.virtualenvs as you.

opencv_dnn.sh Outdated
# Uninstall openCV dependencies, since dnn module installed from source is not recognize by pip
pip uninstall opencv-contrib-python-headless opencv-python-headless


Copy link
Owner

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

You should not add too many new lines in the end.
1 is enough.

flags = {}
data = dict(
version=__version__,
#version=__version__,
Copy link
Owner

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Please merge with the latest master. I have fixed this issue. Thanks.

@vietanhdev vietanhdev merged commit 468eb7b into vietanhdev:master Apr 12, 2023
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

Successfully merging this pull request may close these issues.

2 participants