from grid.model.perception.segmentation.sam2 import SAM2
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
prompts = np.array([[616, 208]])
labels = np.array([1])

model = SAM2(use_local = False)
result = model.run(rgbimage=img, prompts, labels)
print(result.shape)

The SAM2 class implements a wrapper for the Segment Anything 2.1 (SAM2) model, which segments objects in RGB images and videos based on input prompts.

​
class SAM2()
​
use_local
boolean
default:
"False"

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

​
def run()
​
rgbimage
np.ndarray
required

The input RGB image of shape (M,N,3)(M, N, 3).

​
prompts
np.ndarray
required

Points in the form of coordinates of shape (x,y)(x, y) to segment.

​
input_labels
np.ndarray
required

The labels of the points to segment.

​
multimask_output
boolean
default:
"False"

If True, returns a list of masks of shape (M,N)(M,N). Defaults to False. The mutlimask feature is only available for local inference.

​
Returns
np.ndarray

The predicted output.

from grid.model.perception.segmentation.sam2 import SAM2
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
prompts = np.array([[616, 208]])
labels = np.array([1])

model = SAM2(use_local = False)
result = model.run(rgbimage=img, prompts, labels)
print(result.shape)

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

Was this page helpful?

Previous
Sapiens Segmentation
Next