owlv2

from grid_cortex_client import CortexClient, ModelType
import numpy as np
from PIL import Image
client = CortexClient()
image = np.array(Image.open("cat.jpg"))
dets = client.run(ModelType.OWLV2, image_input=image, prompt="a cat")
print(f"Found {len(dets['boxes'])} objects")

from grid_cortex_client import CortexClient
from PIL import Image

client = CortexClient()
image = Image.open("scene.jpg")  # 640x480 RGB
dets = client.run(
    model_id="owlv2",
    image_input=image,
    prompt="building.",
    box_threshold=0.1,
)

print(len(dets["boxes"]))
# 10

# Top detections:
print(dets["scores"][0], dets["boxes"][0])
# 0.152  [122.0, 5.7, 187.9, 227.1]

print(dets["scores"][1], dets["boxes"][1])
# 0.271  [167.7, 26.6, 334.8, 242.4]

print(dets["scores"][2], dets["boxes"][2])
# 0.165  [-0.5, -0.9, 179.5, 242.3]