1766481737214.pdf
13.9 MB
source its a note about machine learning in Amharic its good for introducing
Forwarded from αααα³α αα³α¦α½ π―
This media is not supported in your browser
VIEW IN TELEGRAM
α³αα» α¨ααα αα
α...
αα°α α¨ααα ααα°α΅...
αα α α¨ααα αα αα³...
αα³α α α¨ααα α΅α α΅α...
ααα΅ α¨ααα αα ααα΅...
ααα¨αα¨α α¨ααα ααα³...
ααα΅αΆα΅...β€οΈβπ©Ή
αα°α α¨ααα ααα°α΅...
αα α α¨ααα αα αα³...
αα³α α α¨ααα α΅α α΅α...
ααα΅ α¨ααα αα ααα΅...
ααα¨αα¨α α¨ααα ααα³...
ααα΅αΆα΅...β€οΈβπ©Ή
π’1
Forwarded from The Chill Coding Lounge
If you ever want to build a telegram bot using JavaScript or TypeScript in the most easiest way possible, checkout: https://grammy.dev/
Genuinely made it that much easier to create bots on the fly
Genuinely made it that much easier to create bots on the fly
#Light_based_computing
π€ am just noticing a new way of computing and its lowkey fascinating the future of digital infrastructure have to work in depth again with the analog world
- fastest compute [light based NPU]
- low power demand for more compute [no resistance related power loss ]
i have a lot to learn about this light based computing but the 2 above capture my attention
πthis whole thing is cutting edge to the whole world which means its an active area of research and dev and that just melt my heart β€οΈβ€οΈ
π₯Έi want to learn more in depth this in 2026 and log my finding here as i go
https://www.youtube.com/watch?v=cUBS5WvL2kk
π€ am just noticing a new way of computing and its lowkey fascinating the future of digital infrastructure have to work in depth again with the analog world
- fastest compute [light based NPU]
- low power demand for more compute [no resistance related power loss ]
i have a lot to learn about this light based computing but the 2 above capture my attention
πthis whole thing is cutting edge to the whole world which means its an active area of research and dev and that just melt my heart β€οΈβ€οΈ
π₯Έi want to learn more in depth this in 2026 and log my finding here as i go
https://www.youtube.com/watch?v=cUBS5WvL2kk
Yared kassa
#Light_based_computing π€ am just noticing a new way of computing and its lowkey fascinating the future of digital infrastructure have to work in depth again with the analog world - fastest compute [light based NPU] - low power demand for more computeβ¦
π€ Ya this gives me the vibe that photonic computing is where the future meet the present. This paper is the culprit of this vibe π https://opg.optica.org/optcon/fulltext.cfm?uri=optcon-4-8-1810
This media is not supported in your browser
VIEW IN TELEGRAM
Abenezer Alemayhu Architect | Ai | Film maker from Ehud Ai Studio Β· Mekelle University
He is just so creative
He is just so creative
π₯3
Yared kassa
Abenezer Alemayhu Architect | Ai | Film maker from Ehud Ai Studio Β· Mekelle University He is just so creative
look how he blend culture with AI for me Abni is a pro in his field π₯Έ
Yared kassa pinned Β«π€ Ya this gives me the vibe that photonic computing is where the future meet the present. This paper is the culprit of this vibe π https://opg.optica.org/optcon/fulltext.cfm?uri=optcon-4-8-1810Β»
α³α
α³α΅ 19π― α₯αα³α αα
α±α΅ αα₯αα€α α αα³α αα³α°α’α« αα₯α¨ α α α α α°α¨α³α½α α α°α¨α°α
β€2
FlashPortrait - 6 time Faster Infinite Portrait Animation.pdf
28.3 MB
π₯Έ Well I Found This Pare Interesting Today
Yared kassa
FlashPortrait - 6 time Faster Infinite Portrait Animation.pdf
The FlashPortrait team realized that current AI models are too slow and often fail to keep a personβs face consistent in long videosβthe face eventually starts to look like someone else. Their solution was a new method that locks the subject's identity in place while generating the video.
They introduced a specific "normalization block" that aligns facial features with the video generation process, ensuring the face never distorts or morphs. To handle infinite-length animations smoothly, they used a sliding window method that gently blends overlapping frames.
Crucially, they found a way to speed things up significantly. By using "adaptive latent prediction," the model anticipates future steps rather than calculating every single one, making the process six times faster than existing methods. In short, they built a model that creates long, high-quality portrait animations instantly and accurately, solving the "identity drift" problem without needing any extra editing tools.
They introduced a specific "normalization block" that aligns facial features with the video generation process, ensuring the face never distorts or morphs. To handle infinite-length animations smoothly, they used a sliding window method that gently blends overlapping frames.
Crucially, they found a way to speed things up significantly. By using "adaptive latent prediction," the model anticipates future steps rather than calculating every single one, making the process six times faster than existing methods. In short, they built a model that creates long, high-quality portrait animations instantly and accurately, solving the "identity drift" problem without needing any extra editing tools.
Yared kassa
The FlashPortrait team realized that current AI models are too slow and often fail to keep a personβs face consistent in long videosβthe face eventually starts to look like someone else. Their solution was a new method that locks the subject's identity inβ¦
Framework: They used PyTorch, specifically built for the Hugging Face Diffusers library.
GPU: This is not for a standard gaming PC. The main model file is 57 GB, which is massive. Even the most powerful consumer card (like an RTX 4090) only has 24 GB of memory. To run this, you would need professional-grade hardware (like NVIDIA A100s) or at least two top-tier consumer cards linked together to handle the load.
GPU: This is not for a standard gaming PC. The main model file is 57 GB, which is massive. Even the most powerful consumer card (like an RTX 4090) only has 24 GB of memory. To run this, you would need professional-grade hardware (like NVIDIA A100s) or at least two top-tier consumer cards linked together to handle the load.
π±1π€1
The Orthodox community celebrates this day (Tahsas 19 in the Ethiopian calendar) Evry year as the great annual Nigs of Saint Gabriel the Archangel, widely known as Kulubi Gabriel.
Today we celebrate and honor what God did through the Archangel.
To Honor the Miracle: Believers celebrate God's power shown through Gabriel's intervention. it remind us that faith is stronger than "fire" or any other worldly challenge.
its a local version of Thanksgiving Millions of Ethiopians travel to the Kulubi Gabriel church (near Dire Dawa) and other Gabriel churches in this day.
They thank Saint Gabriel for his holy intercession. He is a swift messenger who carries the believers' prayers up to God. He plead for Godβs mercy on their behalf. for that in this day peoples show how thankful they are for the answered prayers regarding health, children, or safety.
Today we celebrate and honor what God did through the Archangel.
To Honor the Miracle: Believers celebrate God's power shown through Gabriel's intervention. it remind us that faith is stronger than "fire" or any other worldly challenge.
its a local version of Thanksgiving Millions of Ethiopians travel to the Kulubi Gabriel church (near Dire Dawa) and other Gabriel churches in this day.
They thank Saint Gabriel for his holy intercession. He is a swift messenger who carries the believers' prayers up to God. He plead for Godβs mercy on their behalf. for that in this day peoples show how thankful they are for the answered prayers regarding health, children, or safety.
β€2
Iβm currently recovering and extending my old research on GeΚ½ez / Amharic OCR to make it more practical and usable.
After a long break from OCR and machine learning in general, I decided to revisit the project and document my progress as I go.
I'm training my own new model for that purpose for Geez based handwritten character recognition using a dataset my team and I collected back on campus.
am here After finding out about Kaggle, and am trying it! The training is underway as I write this post π€. Hope I get good accuracy without overfitting π€.
After a long break from OCR and machine learning in general, I decided to revisit the project and document my progress as I go.
I'm training my own new model for that purpose for Geez based handwritten character recognition using a dataset my team and I collected back on campus.
am here After finding out about Kaggle, and am trying it! The training is underway as I write this post π€. Hope I get good accuracy without overfitting π€.
The training is taking forever after 2 Hr it haven't even reached halfway yet but from the way the model is learning i have assessed the need to lower the learning rate and i might also need to augment the dataset more so it can simulate more noise the actual real world scenario might bring for the next training. am also planning to test the new transformer concept in here π just to get my hand dirty and know more about it even though using it here is an overkill my planed augmentation will boost the total dataset well above 300k a simple CNN-Attention block or a lightweight Transformer encoder is feasible
Yared kassa
β
It's completed now and i Got the accuracy of 63% in testing data which is good for starting point am glad there is no severe over or underfitting here but the model has reached a performance plateau, which i have to addressing next.
π₯Ί After almost 4 hours of training, I realized Kaggle provides GPU and TPU acceleration.
After switching, the same training finished in ~30 minutes. Lesson learned the hard way. π€
Iβm now augmenting the dataset and preparing it for a Transformer-based approach in the next iteration.
After switching, the same training finished in ~30 minutes. Lesson learned the hard way. π€
Iβm now augmenting the dataset and preparing it for a Transformer-based approach in the next iteration.