πŸ’‘ Remember Box
10 subscribers
2.1K photos
27 videos
1.8K files
11K links
πŸ“ Interesting articles
πŸ—ž Ideas & TodoπŸ’‘
πŸ‘“ Random stuff
🎢 Music
πŸ€” Thoughts
πŸ“• Books
πŸ“š Courses
πŸ“Ί Videos
πŸ“ Papers
πŸ•Έ Websites/Blogs
πŸŽ™ Podcasts
πŸ„ Spirituality

In the pursuit of excellence!

The aim is to discover interesting ideas and perspectives.
Download Telegram
πŸ’‘ Remember Box pinned Β«https://github.com/IDEA-Research/Grounded-SAM-2Β»
Florence-2 (~50M), Grounding DINO (~40M), SAM-2 (~30M), totaling ~120M parameters, much larger than Grounding DINO + FastSAM (~10M)
Accuracy (IoU for semantic segmentation, mAP for instance detection, area error)Speed (inference time for a 256x256 image)Model Size (parameters, disk space, GPU memory)Building Code Compliance (ability to exclude non-habitable spaces and apply code rules)Label Processing (text recognition accuracy and integration)Complexity (ease of implementation, number of models, etc.)