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

Better Installation Instructions #95

Merged
merged 2 commits into from
Jun 28, 2023

Conversation

FrancescoSaverioZuppichini
Copy link
Contributor

Better installation doc in README, mainly

conda env create python=3.7 -f environment.yml
conda activate stylegan3

Then install the additional requirements

pip install -r requirements

Working on a Ubuntu Machine (22.04) with 3090

Francesco Saverio Zuppichini added 2 commits June 27, 2023 18:27
Better installation doc in README
@chrisbward
Copy link

I've used;

python3.10 -m venv ./.venv
source ./.venv/bin/activate
pip install -r requirements.txt
pip install scipy==1.11.0

@XingangPan XingangPan merged commit a3303cd into XingangPan:main Jun 28, 2023
@FrancescoSaverioZuppichini
Copy link
Contributor Author

I've used;

python3.10 -m venv ./.venv
source ./.venv/bin/activate
pip install -r requirements.txt
pip install scipy==1.11.0

I've tried a similar thing but I had an error with the plugings, I think this is linked to the cuda version that torch is shipped somehow - not sure though!

@Kallamamran
Copy link

I have done the installation with venv and activated it. Running gui.bat I get to the GUI, but Pickle is empty and under recent I only have some online pickles.

image

No matter which one I choose the GUI closes and I end up with this error in the CMD :(

image

My gui.bat is the default file and I have moved the checkpoints to the correct location. They were in the scripts folder after having run the download_models-script

image

Dunno what's wrong?!

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.

None yet

4 participants