MGP-STR

The MGPSTR class implements a wrapper for the MGPSTR (Multi-Granularity Prediction for Scene Text Recognition) model, which recognizes text in images.

boolean

default:"False"

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

This model is currently not available via Cortex.

np.ndarray

required

The input RGB image of shape

(M,N,3)

string

Recognized text from the image.

from grid.model.perception.str.mgp_str import MGPSTR
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 = MGPSTR(use_local = True)
result = model.run(rgbimage=img, prompt=<prompt>)
print(result)

This model is best suited for recognizing text in images (OCR).

License
Source

This code is licensed under the Apache 2.0 License.

⌘I

from grid.model.perception.str.mgp_str import MGPSTR
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 = MGPSTR(use_local = True)
result = model.run(rgbimage=img, prompt=<prompt>)
print(result)

Get Started

Open GRID

GRID Enterprise

Robot API

Simulation

AI Layer

Deployment

Data Generation Pipelines

FAQ