Matas Minelga

Update: Time per step is actually ~0.07s on my machine when running a release build.

Hey, thank you so much! I'm still a rust newbie and this means a lot to me. As you probably saw, this project is still very WIP and missing some...

Hey, it's alright! I've cleaned up the code a bit in the meanwhile. And I see you've just updated yours, neat! I've got to admit, I hadn't run or looked...

I'm also a Python developer with experience in C++ and I'd love to help however I can (getting my Quest soon)

To add, I've tried every multi-tap timeout from `wait forever` to `fastest`. Though it does seem to happen mostly in the `Messenger` app. I'm not able to reproduce it in...

I see I've already submitted the same bug report 2 years ago. Any chance of getting a fix? :sweat_smile: https://github.com/AnySoftKeyboard/AnySoftKeyboard/issues/2293

Just `pip install torch scipy imageio torchvision scikit-image tensorboardX` and you'll be good to go.

@R4ZZ3 >And that install command won't install cudatoolkit which I want for speed. Well, that is very specific to `conda`, which is not used by everyone. I modified the code...

I'll just add these **really** hacky instructions for now, I'll fix it up in my fork soon 1. Copy the code contents to the `test.py` file 1. Create `checkpoints` directory...

I'm happy to help! I've also created a clean version of `image_upscaler.py`, check it out on my branch: https://github.com/ashirviskas/DeFiAN/tree/general_refactor