ovsegmentation 1.0.2

Open vocabulary detection and segmentation package

Open vocabulary segmentation

Installation

pip install ovsegmentation
pip install git+https://github.com/NVIDIA-AI-IOT/torch2trt.git

Models

• GroundingDINO
• MobileSAMv2

Usage

Get detection

from ovsegmentation import build_segmentator, visualize, get_waypoint, OVSegmentation
input_data = {
    "image": image,
    "text": ovd_prompt,
    "depth": depth_image,
    "intrinsics": intrinsics,
}
    
ovs = build_segmentator(weights_path='weights')

res = ovs.get_detections(input_data)

Visualize

annotated_image, labels = visualize(
    image, res, instance_random_color=True, draw_bbox=True
)
plt.figure(figsize=(15, 8))
plt.imshow(annotated_image)
plt.show()

Weights structure

Weights structure:

• WEIGHTS_DIR/MobileSAMv2/l2_encoder.engine
• WEIGHTS_DIR/MobileSAMv2/mobilesamv2_decoder.engine
• WEIGHTS_DIR/MobileSAMv2/ObjectAwareModel.engine
• WEIGHTS_DIR/GroundingDINO/groundingdino_swint_ogc.pth

weights_path: WEIGHTS_DIR