Like the original SAM, SAM 2 can be applied out of the box to a diverse range of real-world use cases and we’re excited to see what developers build with it. Try the demo https://
go.fb.me/2z6k3v
Get the code
@aiatmeta
-
SAM 2 Ready for Real-World Applications and Developer Innovation
By
–
-
Meta Releases New Video Segmentation Model and SA-V Dataset
By
–
In addition to the new model, we’re also releasing SA-V, a dataset that’s 4.5x larger + has ~53x more annotations than the largest existing video segmentation dataset.
— AI at Meta (@AIatMeta) 29 juillet 2024
We hope this work will help accelerate new computer vision research ➡️ https://t.co/yeUinLH9lg pic.twitter.com/MoDxeA31hUIn addition to the new model, we’re also releasing SA-V, a dataset that’s 4.5x larger + has ~53x more annotations than the largest existing video segmentation dataset. We hope this work will help accelerate new computer vision research https://
go.fb.me/yck7bu -
Meta Launches SAM 2 for Real-Time Object Segmentation in Images and Videos
By
–
Introducing Meta Segment Anything Model 2 (SAM 2) — the first unified model for real-time, promptable object segmentation in images & videos.
— AI at Meta (@AIatMeta) 29 juillet 2024
SAM 2 is available today under Apache 2.0 so that anyone can use it to build their own experiences
Details ➡️ https://t.co/eTTDpxI60h pic.twitter.com/mOFiF1kZfEIntroducing Meta Segment Anything Model 2 (SAM 2) — the first unified model for real-time, promptable object segmentation in images & videos. SAM 2 is available today under Apache 2.0 so that anyone can use it to build their own experiences Details https://
go.fb.me/p749s5 -
Foundation Model Research Sharing for Community Understanding
By
–
We hope that sharing this research will help the larger research community understand the key factors of foundation-model development and contribute to a more informed discussion about the future of foundation models in the general public.
-
Meta publishes comprehensive Llama 3 research paper
By
–
As part of our support of open science, we've published the full Llama 3 research paper covering a range of topics.
• Model training
• Model architecture
• Results of our ongoing work on integrating image/video/speech capabilities
• Much more Paper https://
go.fb.me/l5f55z -
Meta releases RFC for Llama Stack API standardization
By
–
Looking ahead we’re aiming to provide developers and platform providers a standard and well-maintained interface to Llama models to improve interoperability. To support this, we’ve released a RFC for something we’re calling “Llama Stack”, a new set of APIs that includes an
-
Llama 3.1 Reference System and Open Source Agentic Applications Released
By
–
With Llama 3.1 we’ve also released a new reference system that includes several sample agentic applications to accelerate the responsible development of new and innovative applications These applications are open source and can be used by the community as a platform to build
-
Llama 3 Models Technical Details and Training Information
By
–
For more technical details on what our latest Llama 3 models are capable of and how they were trained, you can find the model card here https://
go.fb.me/krbww9 -
Access Llama Code and Training Recipes on GitHub
By
–
Want to access the code, new training recipes and more? Check out the official Llama repo on GitHub https://
go.fb.me/wy18hm