PET-DINO

PET-DINO turns a single example box into detections for all look-alike objects in the image. Enable Cascading and every box you draw becomes a new prompt, so dense scenes fill in as you work.

Object DetectionApache-2.0
Recommended7/10
VRAM2.8 GBweights, plus ~0.5 GB reserve
Tools2across 1 annotation type
Runs onmacOSCPU2 of 4 runtime profiles

Install

boat model install pet-dino

Installs pet-dino:swin-t with 2.8 GB of weights into an isolated runtime.

Tools

What PET-DINO adds to the annotation editor. Each example loops what you do and what comes back.

Similar objects example on object detection

Similar objects

BoxBounding boxes

Object Detection

Draw a box around one example. The model finds similar objects and lets you pick which bounding boxes to keep.

  • Pick candidates
Cascading example on object detection

Cascading

BoxBounding boxes

Object Detection

Draw boxes as you normally would. Every new box becomes a prompt, and similar objects are suggested automatically for you to accept.

  • Pick candidates
  • Runs automatically

Tags

Each tag is an installable variant, such as a size or quantization, with its own weights.

TagWeightsPlatformsInstall
pet-dino:swin-tdefault2.8 GB · 6 filesmacOSCPU

Platforms

BOAT picks the runtime profile that matches your machine. Only that profile's code is downloaded.

macOS · Metal

Apple silicon (MPS)

Python 3.11 · 1 MB

Linux · CUDA 12.8

NVIDIA, incl. Blackwell

Not supported

Linux · CUDA 12.6

NVIDIA GPUs

Not supported

Linux · CPU

x86_64 CPU

Python 3.11 · 1 MB

License

BOAT's adapter code is Apache-2.0. The model's own code and weights keep their upstream license:Apache-2.0.

Bundled license files: BOAT-APACHE-2.0.txt, NOTICE.md, UPSTREAM-LICENSE.txt

Package details

Package
pet-dino
Version
0.0.1
Type
Common model
BOAT Core
≥ 0.1.0 · < 1.0.0
Idle unload
300s (change with boat model setup)
Inference timeout
600s
Manifest SHA-256
a490d57917820240eb1ce1dc22b89dbd2b7830fa643d80a7c3133f5522d0b1b5
Upstream notice
BOAT adapter code is Apache-2.0. Upstream model code and weights keep their own licenses.

Model: pet-dino
Pinned weight provenance is in ../weights.json. Vendored code revisions, when present,
are recorded in ../vendor/UPSTREAM_REVISION. The local macOS adaptations are retained.
Runtime dependencies are installed from pinned distributions with their own license files.
↑↓ navigate↵ open