This is the Linux app named Segment Anything whose latest release can be downloaded as segment-anythingsourcecode.tar.gz. It can be run online in the free hosting provider OnWorks for workstations.
Download and run online this app named Segment Anything with OnWorks for free.
Bu uygulamayı çalıştırmak için şu talimatları izleyin:
- 1. Bu uygulamayı PC'nize indirdiniz.
- 2. Dosya yöneticimize https://www.onworks.net/myfiles.php?username=XXXXX istediğiniz kullanıcı adını girin.
- 3. Bu uygulamayı böyle bir dosya yöneticisine yükleyin.
- 4. Bu web sitesinden OnWorks Linux çevrimiçi veya Windows çevrimiçi öykünücüsünü veya MACOS çevrimiçi öykünücüsünü başlatın.
- 5. Yeni başladığınız OnWorks Linux işletim sisteminden, istediğiniz kullanıcı adıyla https://www.onworks.net/myfiles.php?username=XXXXX dosya yöneticimize gidin.
- 6. Uygulamayı indirin, kurun ve çalıştırın.
EKRAN
Ad
Her Şeyi Bölümlere Ayırın
AÇIKLAMA
Segment Anything (SAM) is a foundation model for image segmentation that’s designed to work “out of the box” on a wide variety of images without task-specific fine-tuning. It’s a promptable segmenter: you guide it with points, boxes, or rough masks, and it predicts high-quality object masks consistent with the prompt. The architecture separates a powerful image encoder from a lightweight mask decoder, so the heavy vision work can be computed once and the interactive part stays fast. A bundled automatic mask generator can sweep an image and propose many object masks, which is useful for dataset bootstrapping or bulk annotation. The repository includes ready-to-use weights, Python APIs, and example notebooks demonstrating both interactive and automatic modes. Because SAM was trained with an extremely large and diverse mask dataset, it tends to generalize well to new domains, making it a practical starting point for research and production annotation tools.
Özellikler
- Promptable segmentation from points, boxes, or coarse masks
- Fast mask decoder on top of a precomputed image embedding
- Automatic mask generation for exhaustive object proposals
- Pretrained checkpoints and simple Python inference APIs
- Example notebooks and scripts for interactive annotation workflows
- Outputs in common formats for easy integration into labeling tools
Kategoriler
This is an application that can also be fetched from https://sourceforge.net/projects/segment-anything.mirror/. It has been hosted in OnWorks in order to be run online in an easiest way from one of our free Operative Systems.
