Forwarded from PythonDigest
Визуальное RPG с долговременной памятью, генерируемое из 3 нейросетей и LLamы
https://ift.tt/XNe5nZf
Языковые модели (NLP) сейчас активно развиваются и находят себе всё больше интересных применений. Начиналась же их эпоха с классики жанра — D&D. Это настольная игра, где несколько друзей или просто знакомых синхронно галлюцинируют, представляя себя командой героев в некоем вымышленном мире. Прав же во внутриигровых выборах тот, кто выкинул большее число на игральной кости. Судить сейчас об их мотивации у меня нет никакого желания, да и статья вообще-то не об этом.
https://ift.tt/XNe5nZf
Языковые модели (NLP) сейчас активно развиваются и находят себе всё больше интересных применений. Начиналась же их эпоха с классики жанра — D&D. Это настольная игра, где несколько друзей или просто знакомых синхронно галлюцинируют, представляя себя командой героев в некоем вымышленном мире. Прав же во внутриигровых выборах тот, кто выкинул большее число на игральной кости. Судить сейчас об их мотивации у меня нет никакого желания, да и статья вообще-то не об этом.
Forwarded from HN Best Comments
Re: iNaturalist strikes out on its own
I reverse engineered their stuff a bit. I downloaded their Android APK and found a tensorflow lite model inside. I found that it accepts 299x299px RGB input and spits out probabilities/scores for about 25,000 species. The phylogenetic ranking is performed separately (outside of the model) based on thresholds (if it isn't confident enough about any species, it seems to only provide genus, family, etc.) They just have a CSV file that defines the taxonomic ranks of each species.
I use it to automatically tag pictures that I take. I took up bird photography a few years ago and it's become a very serious hobby. I just run my Python noscript (which wraps their TF model) and it extracts JPG thumbnails from my RAW photos, automatically crops them based on EXIF data (regarding the focus point and the focus distance) and then feeds it into the model. This cropping was critical - I can't just throw the model a downsampled 45 megapixel image straight from the camera, usually the subject is too small in the frame. I store the results in a sqlite database. So now I can quickly pull up all photos of a given species, and even sort them by other EXIF values like focus distance. I pipe the results of arbitrary sqlite queries into my own custom RAW photo viewer and I can quickly browse the photos. (e.g. "Show me all Green Heron photos sorted by focus distance.") The species identification results aren't perfect, but they are very good. And I store the score in sql too, so I can know how confident the model was.
One cool thing was that it revealed that I had photographed a Blackpoll Warbler in 2020 when I was a new and budding birder. I didn't think I had ever seen one. But I saw it listed in the program results, and was able to confirm by revisiting the photo.
I don't know if they've changed anything recently. Judging by some of their code on GitHub, it looked like they were also working on considering location when determining species, but the model I found doesn't seem to do that.
I can't tell you anything about how the model was actually trained, but this information may still be useful in understanding how the app operates.
Of course, I haven't published any of this code because the model isn't my own work.
fogleman, 6 hours ago
I reverse engineered their stuff a bit. I downloaded their Android APK and found a tensorflow lite model inside. I found that it accepts 299x299px RGB input and spits out probabilities/scores for about 25,000 species. The phylogenetic ranking is performed separately (outside of the model) based on thresholds (if it isn't confident enough about any species, it seems to only provide genus, family, etc.) They just have a CSV file that defines the taxonomic ranks of each species.
I use it to automatically tag pictures that I take. I took up bird photography a few years ago and it's become a very serious hobby. I just run my Python noscript (which wraps their TF model) and it extracts JPG thumbnails from my RAW photos, automatically crops them based on EXIF data (regarding the focus point and the focus distance) and then feeds it into the model. This cropping was critical - I can't just throw the model a downsampled 45 megapixel image straight from the camera, usually the subject is too small in the frame. I store the results in a sqlite database. So now I can quickly pull up all photos of a given species, and even sort them by other EXIF values like focus distance. I pipe the results of arbitrary sqlite queries into my own custom RAW photo viewer and I can quickly browse the photos. (e.g. "Show me all Green Heron photos sorted by focus distance.") The species identification results aren't perfect, but they are very good. And I store the score in sql too, so I can know how confident the model was.
One cool thing was that it revealed that I had photographed a Blackpoll Warbler in 2020 when I was a new and budding birder. I didn't think I had ever seen one. But I saw it listed in the program results, and was able to confirm by revisiting the photo.
I don't know if they've changed anything recently. Judging by some of their code on GitHub, it looked like they were also working on considering location when determining species, but the model I found doesn't seem to do that.
I can't tell you anything about how the model was actually trained, but this information may still be useful in understanding how the app operates.
Of course, I haven't published any of this code because the model isn't my own work.
fogleman, 6 hours ago
Forwarded from Good Shit™️😤😤
https://github.com/forkgram/tdesktop/releases/tag/v4.8.1 so kotatogram was a bust, as it's so old i can't fuckin see spoilers, but here's the last forkgram release before stories got implemented.
GitHub
Release Forkgram v4.8.1 · forkgram/tdesktop
— Updated version to 4.8.1.
Forwarded from Good Shit™️😤😤
https://www.navidrome.org/ go make your own spotify
Navidrome
Welcome to Navidrome! Learn More Download Your Personal Streaming Service
Navidrome allows you to enjoy your music collection from anywhere, by making it available through a modern Web UI and through a wide range of third-party compatible mobile apps, for…
Navidrome allows you to enjoy your music collection from anywhere, by making it available through a modern Web UI and through a wide range of third-party compatible mobile apps, for…
Forwarded from Good Shit™️😤😤
https://github.com/fgsfdsfgs/perfect_dark has reached "playable" for windows/linux builds, currently in a somewhat janky state, graphical glitches and the like.
nonetheless, here's the current build with rom file added. no support offered by myself, but if you wanna play around with it go ham.
nonetheless, here's the current build with rom file added. no support offered by myself, but if you wanna play around with it go ham.
GitHub
GitHub - fgsfdsfgs/perfect_dark: work in progress port of n64decomp/perfect_dark to modern platforms
work in progress port of n64decomp/perfect_dark to modern platforms - fgsfdsfgs/perfect_dark
CoreCtrl / CoreCtrl · GitLab
https://gitlab.com/corectrl/corectrl
https://gitlab.com/corectrl/corectrl
GitLab
CoreCtrl / CoreCtrl · GitLab
Profile based system control utility
Forwarded from Tech Crimes (Architector #4)
"The goal of this project is to stop the Windows compositor (dwm.exe) to improve game performances by using exclusive fullscreen. We cannot disable the compositor properly since Windows 8. The program provide a simple window to disable/enable the compositor.
it kills explorer.exe and dwm.exe dynamically. It also suspends winlogon.exe"
https://github.com/nebuloss/killer
it kills explorer.exe and dwm.exe dynamically. It also suspends winlogon.exe"
https://github.com/nebuloss/killer
GitHub
GitHub - nebuloss/killer: disable compositor on Windows 10
disable compositor on Windows 10. Contribute to nebuloss/killer development by creating an account on GitHub.
Forwarded from Пятничный деплой
очень обстоятельное и довольно исчерпывающее руководство как построить себе selfhosting сервисы (местами, правда немного неактуально) https://github.com/mikeroyal/Self-Hosting-Guide
GitHub
GitHub - mikeroyal/Self-Hosting-Guide: Self-Hosting Guide. Learn all about locally hosting (on premises & private web servers)…
Self-Hosting Guide. Learn all about locally hosting (on premises & private web servers) and managing software applications by yourself or your organization. Including Cloud, LLMs, WireGuar...
Forwarded from /usr/bin
Forwarded from PythonDigest
pysentation - CLI for Displaying Python Presentations
https://ift.tt/ZNcvKFw
https://ift.tt/ZNcvKFw
Forwarded from Технологический Болт Генона
Пятницы псто
Всем хороших выходных! ❤️
[Project] Retrocomputing in Docker
https://github.com/retroprom/docker
Всем хороших выходных! ❤️
[Project] Retrocomputing in Docker
https://github.com/retroprom/docker