Feedback from running inference on Win10
Norod opened this issue · 3 comments
I'm on conda 4.9.2, Windows 10 64bit
In case anyone finds it useful, then:
I had to run
conda install -c anaconda cmake
To get CMAKE into the environment, however, for some reason pip has failed to install ninja from source.
So after activating the environment, I did the following steps which did not get executed due to the ninja build fail:
conda install ninja==1.10.0
conda install tqdm==4.59.0 gitpython scikit-learn
pip install gpustat
pip install tensorboard==2.4.1
pip install -e .
pip install omegaconf click
I was then able to run the inference notebook and generate a lovely panoramic image
To generate the video, I had to first run:
conda install -c conda-forge opencv
To get opencv into the environment
The video was then generated and it looks beautiful.
Cheers!
@Norod Thank you for the advice! We didn't have a chance to test the model on a Windows machine.
Also, for Windows users, it might also be helpful to check the original StyleGAN2-ADA repo requirements or installation instructions since we inherited almost all the dependencies from it.
@universome That's very legitimate :) Perhaps adding note to the README.MD that the code is known to work but not tested on Windows? a link to this issue page and/or the original repo's requirements? (Thank you for that, BTW, it's helpful) Anyway, awesome work!
@Norod yeah, that's a good idea. I added the link to this issue into README.md