Grounded SAM 2

The GSAM2 class provides a wrapper for the GSAM2 model, which combines the power of Grounding DINO for text-based object detection with SAM2 for high-precision segmentation in RGB images.

boolean

default:"False"

If True, inference call is run on the local VM, else offloaded onto GRID-Cortex. Defaults to False.

np.ndarray

required

The input RGB image of shape

(M, N, 3)

str

required

The text prompt to use for segmentation.

np.ndarray

The predicted segmentation mask of shape

(M, N)

from grid.model.perception.segmentation.gsam2 import GSAM2
car = AirGenCar()

# We will be capturing an image from the AirGen simulator 
# and run model inference on it.

img =  car.getImage("front_center", "rgb").data

model = GSAM2(use_local = False)
result = model.run(rgbimage=img, prompt=<prompt>)
print(result.shape)

License
Source

This code is licensed under the Apache 2.0 and BSD-3 License.

from grid.model.perception.segmentation.gsam2 import GSAM2 car = AirGenCar() # We will be capturing an image from the AirGen simulator # and run model inference on it. img = car.getImage("front_center", "rgb").data model = GSAM2(use_local = False) result = model.run(rgbimage=img, prompt=<prompt>) print(result.shape)

Get Started

Open GRID

GRID Enterprise

Robot API

Simulation

AI Layer

Deployment

Data Generation Pipelines

FAQ