The view is now sorted by last created by default. Maybe most stars https://gitlab.com/traffxml?sort=stars_desc (and last created for repos with the same starts) is a better default sort?
I'm surprised that article doesn't discuss Uber Eats which brings in more revenue that the taxi part (called Mobility by Uber, both are 13b in the quarter that ended June 30, 2022 https://investor.uber.com/news-events/news/press-release-det... ). Lyft doesn't have this revenue.
I'm stuck on 'RuntimeError: expected scalar type BFloat16 but found Float' too. Most relevant links seems https://github.com/CompVis/stable-diffusion/pull/47 but I'm not sure. Please post when there is a solution.
That might have to do with your Mac OS version. Pre-12.4 Mac OS does not allow the Torch backend to use the M1 GPU, and so the script attempts to use the cpu, but then the cpu does not support half-precision numbers.
Yep---that was it in my case. I had the same error but it went away after upgrading to MacOS 12.5. You should actually check if your PyTorch installation can detect the mps backend: `torch.backends.mps.is_available()` must be equal to True.
Great article. The author mentions: "Machine learning models can now create text and images for zero marginal cost". Another step was just taken in this direction with TikTok launching an 'AI greenscreen' based on text prompts https://techcrunch.com/2022/08/15/tiktok-in-app-text-to-imag...
BTW The repo with the specification seems to be https://gitlab.com/traffxml/traff and it contains a presentation with more context https://gitlab.com/traffxml/traff/-/blob/master/TraFF%20Pres...