You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
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:
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:
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.
The text was updated successfully, but these errors were encountered: