Grounded SAM

The GroundedSAM class provides a wrapper for the GroundedSAM model, which segments objects in RGB images based on text prompts.

class GroundedSAM()

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 $(M, N, 3)$ .

prompt

str

required

The text prompt to use for segmentation.

Returns

np.ndarray

The predicted segmentation mask of shape $(M, N)$ .

This code is licensed under the Apache 2.0 License.