OneFormer

The OneFormer class provides core functionality for this module.

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

default:"semantic"

The mode of segmentation. Can be either “semantic” or “panoptic”. Defaults to “semantic”.

np.ndarray

The predicted segmentation mask of shape

(M, N)

from grid.model.perception.segmentation.oneformer import OneFormer
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 = OneFormer(use_local = False)
result = model.run(rgbimage=img, mode="semantic")
print(result.shape)

License
Source

This code is licensed under the MIT License.

⌘I

from grid.model.perception.segmentation.oneformer import OneFormer
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 = OneFormer(use_local = False)
result = model.run(rgbimage=img, mode="semantic")
print(result.shape)

Get Started

Open GRID

GRID Enterprise

Robot API

Simulation

AI Layer

Deployment

Data Generation Pipelines

FAQ