Skip to main content
The GroundingDINO implements a wrapper for the GroundingDINO model, which detects objects in RGB images based on text prompts.
float
default:"0.4"
Confidence threshold for bounding box detection.
float
default:"0.25"
Confidence threshold for text-based object detection.
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)(M,N,3).
str
required
Text prompt for object detection. Multiple prompts can be separated by a ”.”.
List[float], List[float], List[str]
Returns three lists: bounding boxes coordinates, confidence scores, and label strings.
This code is licensed under the Apache 2.0 License.