It's time to get out of stealth 👋
Today, we are launching @monogram_ai and announcing our $40m seed round led by DST and Lux Capital.
Monogram is the first AI app that was built around a visual interface, from the ground up.
We created a technology that generates an entire user interface on the fly, in just a few seconds. Ask anything, and instead of staring at a wall of text, you get an interactive visual response.
I was using Twitter mainly for work, and followed people working on ML/DL, image processing, software, etc. . Most of the content shown to me, not coming from people I followed anymore. I will be utilizing more focused mediums.
@paravatar @loicaroyer @jenscs83 @HamamatsuPhoton I see. Thank you for notifying us. I will fix those and notify you. Meanwhile please let me know if I can help with anything else regarding Aydin!
@paravatar @loicaroyer @jenscs83 @HamamatsuPhoton That seems to be an older link. We added versioning to our docs. You can now reach to same page here:https://t.co/oRbPjDhysU ,also please let me know if you find any older broken links on https://t.co/qZsLjhUrgD
🧙♂️What sorcery is that? Want to learn how to do this with your own images? and have a quick primer on image denoising? @_ahmetcansolak and I recorded an intro on image denoising and a tutorial on https://t.co/lWUpy4vp1h here:
https://t.co/cUO4zPWITo
@MRtmfm#Aydin
@jenscs83 @HamamatsuPhoton@loicaroyer I've never benchmarked Aydin on threadripper indeed. Which denoising algorithm are you using? Roughly how long it takes to train and infer on your full-stack?
@jenscs83 @HamamatsuPhoton@loicaroyer I see, Aydin FGR denoisers support upto 4 spatio-temporal dimensions. xyzt, xyz, xyt all accepted. If you are selecting a too small training crop it will give same warning and not use CUDA. That's the main reason for that warning, as we can go faster on CPU for small enough crops
@jenscs83 @HamamatsuPhoton@loicaroyer If you could let me know more about your data, I can possibly help better. Feel free to send me a message with more details!
@jenscs83 @HamamatsuPhoton@loicaroyer Do you have separate images for each time point? If so you can create a hyperstack and can choose to treat that new dimension as a spatio-temporal dimension in Dimensions tab. Btw, that warning only for feature generation, FGR-CatBoost algorithm able to use CUDA GPUs for training
Releasing 🌟nerfstudio🌟, a plug-and-play python library to easily create your own NeRFs!
@nerfstudioteam is a contributor friendly open-source repo with a realtime web viewer that makes it easy to make cool videos 📽️
https://t.co/zw0ZPqIZ4c
https://t.co/NZM8GPjNrF #nerfstudio 1/
Ses işlemeyle ilgileniyor ve Python kullanan iyi bir kaynak bulmakta zorlanıyor musunuz? Yardımcı olmama izin verin: https://t.co/gDgZNPl6IZ
Not: Sevgili hocam Barış Bozkurt tarafından yazılmıştır (Teşekkürler Barış hocam)
@kchev@github@GitHubCommunity @GitHubHelp That would be better than the existing tabs too. I personally use wide enough windows to render these tabs side-by-side. I believe these can be implemented in a responsive manner to improve experience for more users with varying setups. @github
Here is a UX/UI idea that can boost productivity on @github : Rendering Write and Preview tabs side-by-side on the new issue/new PR pages. Life would be much better if I didn't need to go between Write and Preview tabs back and forth. @github@GitHubCommunity @GitHubHelp