label_processing.label_rotation

Label Rotation Module (TensorFlow)

Predicts and corrects the orientation of label images using a trained TensorFlow classification model that outputs one of four angle classes (0°, 90°, 180°, 270°). Used by the traditional pipeline; the Gemini pipeline determines rotation angles via the Gemini API instead.

Functions

debug_save_by_angle(image_paths, ...)	Copy images into angle-named subdirectories for visual debugging.
get_image_paths(input_image_dir)	Get a list of image paths in the input directory.
get_predicted_angles(model, images)	Predict angles for a list of images using a trained model.
load_image(image_path)	Load an image from a file path.
load_images(image_paths)	Load images from a list of image paths.
predict_angles(input_image_dir, ...[, debug])	Load a trained model, predict angles for input images, and rotate images accordingly.
rotate_image(image, angle)	Rotate an image based on a given angle.
rotate_image_pil(image_path, angle_deg, ...)	Rotate an image using PIL and save the result.
rotate_images(image_paths, predicted_angles, ...)	Rotate images based on their predicted angles and save them to the output directory.
rotate_single_image(image_path, angle, ...)	Rotate a single image based on a given angle and save the rotated image.
save_image(image, output_path)	Save an image to a file path.