Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.generalrobotics.dev/llms.txt

Use this file to discover all available pages before exploring further.

The Metric3D class provides a wrapper for the Metric3D model, which estimates depth maps from RGB images using a variety of encoder types.
​
class Metric3D()
​
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).
​
Returns
np.ndarray
The predicted depth map of shape (M,N)(M,N).
from grid.model.perception.depth.metric3d import Metric3D
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 = Metric3D(use_local = False)
result = model.run(rgbimage=img)
print(result.shape)
This code is licensed under the BSD 2-Clause License.