Skip to content

Latest commit

 

History

History
121 lines (89 loc) · 3.62 KB

README.md

File metadata and controls

121 lines (89 loc) · 3.62 KB
logo

Osam

Get up and running with promptable vision models locally.




Osam (/oʊˈsɑm/) is a tool to run open-source promptable vision models locally (inspired by Ollama).

Osam provides:

  • Promptable Vision Models - Segment Anything Model (SAM), EfficientSAM, YOLO-World;
  • Local APIs - CLI & Python & HTTP interface;
  • Customization - Host custom vision models.

Installation

Pip

pip install osam

For osam serve:

pip install osam[serve]

Quickstart

To run with EfficientSAM:

osam run efficientsam --image <image_file>

To run with YOLO-World:

osam run yoloworld --image <image_file>

Model library

Here are models that can be downloaded:

Model Parameters Size Download
SAM 100M 100M 100MB osam run sam:100m
SAM 300M 300M 300MB osam run sam:300m
SAM 600M 600M 600MB osam run sam
EfficientSAM 10M 10M 40MB osam run efficientsam:10m
EfficientSAM 30M 30M 100MB osam run efficientsam
YOLO-World XL 100M 400MB osam run yoloworld

PS. sam, efficientsam is equivalent to sam:latest, efficientsam:latest.

Usage

CLI

# Run a model with an image
osam run efficientsam --image examples/_images/dogs.jpg > output.png

# Get a JSON output
osam run efficientsam --image examples/_images/dogs.jpg --json
# {"model": "efficientsam", "mask": "..."}

# Give a prompt
osam run efficientsam --image examples/_images/dogs.jpg \
  --prompt '{"points": [[1439, 504], [1439, 1289]], "point_labels": [1, 1]}' \
  > efficientsam.png
osam run yoloworld --image examples/_images/dogs.jpg --prompt '{"texts": ["dog"]}' \
  > yoloworld.png


Input and output images ('dogs.jpg', 'efficientsam.png', 'yoloworld.png').

Python

import osam.apis
import osam.types

request = osam.types.GenerateRequest(
    model="efficientsam",
    image=np.asarray(PIL.Image.open("examples/_images/dogs.jpg")),
    prompt=osam.types.Prompt(points=[[1439, 504], [1439, 1289]], point_labels=[1, 1]),
)
response = osam.apis.generate(request=request)
PIL.Image.fromarray(response.mask).save("mask.png")


Input and output images ('dogs.jpg', 'mask.png').

HTTP

# pip install osam[serve]  # required for `osam serve`

# Get up the server
osam serve

# POST request
curl 127.0.0.1:11368/api/generate -X POST \
  -H "Content-Type: application/json" \
  -d "{\"model\": \"efficientsam\", \"image\": \"$(cat examples/_images/dogs.jpg | base64)\"}" \
  | jq -r .mask | base64 --decode > mask.png