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

Tutorial on how to Install and Run the Model on Windows - Not an issue #117

Open
AleksandarHaber opened this issue Feb 1, 2025 · 0 comments

Comments

@AleksandarHaber
Copy link

AleksandarHaber commented Feb 1, 2025

I created a video tutorial on how to properly install Janus-Pro on a Windows computer:

https://www.youtube.com/watch?v=4k4XcvxvVuA

While trying to install the software on a Windows computer, I experienced several issues. One of the issues is that after following the installation method suggested on the GitHub webpage and after running the test code, the following error appears

raise AssertionError("Torch not compiled with CUDA enabled")
AssertionError: Torch not compiled with CUDA enabled

In order to install the software on a Windows computer, you need to manually install the PyTorch with CUDA support. You need to use the command generated here:

https://pytorch.org/get-started/locally/

Also, before installing the Pytorch software in the Python virtual environment, make sure that MS Visual Studio 2022 with C++ compilers is installed as well as NVIDIA CUDA Toolkit. Then you will also have to erase the torch requirement from two files:

requirements.txt

requirements.txt

and

pyproject.toml

pyproject.toml

After that you can run

pip install .

and CUDA Pytorch will be properly recognized.

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

1 participant