metadata
base_model:
- Ultralytics/YOLO11
YOLOv11-pose trained for rotating images to their correct orientation. Works best on images containing faces.
It puts image on a white card, rotates it correctly and crops.
python inference.py -h
usage: inference.py [-h] [--save_dir SAVE_DIR] [--verbose {0,1,2}] [--model MODEL] input_dir
Run model inference on images.
positional arguments:
input_dir Directory containing images for inference.
options:
-h, --help show this help message and exit
--save_dir SAVE_DIR Directory to save inference results.
--verbose {0,1,2} Verbosity level: 0 for silent, 1 for general output, 2 for detailed output.
--model MODEL Path to the YOLO model weights.