|
import copy |
|
|
|
from surya.detection import batch_text_detection |
|
from surya.input.load import load_from_folder, load_from_file |
|
from surya.layout import batch_layout_detection |
|
from surya.model.detection.model import load_model, load_processor |
|
from surya.postprocessing.heatmap import draw_polys_on_image |
|
from surya.settings import settings |
|
import os |
|
|
|
def main(input_path, max_pages=None): |
|
|
|
model = load_model(checkpoint=settings.LAYOUT_MODEL_CHECKPOINT) |
|
processor = load_processor(checkpoint=settings.LAYOUT_MODEL_CHECKPOINT) |
|
det_model = load_model() |
|
det_processor = load_processor() |
|
|
|
if os.path.isdir(input_path): |
|
images, names = load_from_folder(input_path, max_pages) |
|
|
|
else: |
|
images, names = load_from_file(input_path, max_pages) |
|
|
|
|
|
line_predictions = batch_text_detection(images, det_model, det_processor) |
|
|
|
layout_predictions = batch_layout_detection(images, model, processor, line_predictions) |
|
|
|
|
|
for idx, (image, layout_pred, name) in enumerate(zip(images, layout_predictions, names)): |
|
polygons = [p.polygon for p in layout_pred.bboxes] |
|
labels = [p.label for p in layout_pred.bboxes] |
|
bbox_image = draw_polys_on_image(polygons, copy.deepcopy(image), labels=labels) |
|
return bbox_image |