How to set `zoo_url` for a custom model in DeGirum?

General
,
3

error
error1397×497 57.9 KB

import degirum as dg
import cv2

# Load the segmentation model from the model zoo.
# Replace '<path_to_model_zoo>' with the directory path to your model assets.
model = dg.load_model(
    model_name='yolov8n_seg',
    inference_host_address='@local',
    zoo_url='home/pi/hailo_examples/model_zoo'
)

# Run inference on an input image.
# Replace '<path_to_input_image>' with the actual path to your image.
inference_result = model('/home/pi/hailo_examples/assets/panel1.jpg')

# The segmentation overlay (with masks and labels) is available via the image_overlay attribute.
cv2.imshow("Segmentation Output", inference_result.image_overlay)

# Wait until the user presses 'x' or 'q' to close the window.
while True:
    key = cv2.waitKey(0) & 0xFF
    if key == ord('x') or key == ord('q'):
        break

cv2.destroyAllWindows()

I took the example code I wrote above from the GitHub repository and tried running it on the RPi 5 8GB model, but I’m getting an error as shown in the image. You can see that my model exists in the file structure. How can I run my own model?.
The file structure is as follows:
The folder path: home/pi/hailo_examples/model_zoo/
Contents of the folder:

  • yolov8n_seg.hef
  • yolov8n_seg.json
  • labels_coco.json