Commit 6a75d7dc authored by myhloli's avatar myhloli
Browse files

perf(layout): optimize layout detection for PDF extraction

- Add initial setup for layout detection
- Implement conditional cropping for tall images
- Skip cropping for wide images to improve performance
- Reuse Image object across layout detection steps
parent 56b0e18b
......@@ -171,6 +171,10 @@ class CustomPEKModel:
def __call__(self, image):
pil_img = Image.fromarray(image)
width, height = pil_img.size
# logger.info(f'width: {width}, height: {height}')
# layout检测
layout_start = time.time()
layout_res = []
......@@ -179,11 +183,9 @@ class CustomPEKModel:
layout_res = self.layout_model(image, ignore_catids=[])
elif self.layout_model_name == MODEL_NAME.DocLayout_YOLO:
# doclayout_yolo
img_pil = Image.fromarray(image)
width, height = img_pil.size
# logger.info(f'width: {width}, height: {height}')
if height > width:
input_res = {"poly":[0,0,width,0,width,height,0,height]}
new_image, useful_list = crop_img(input_res, img_pil, crop_paste_x=width//2, crop_paste_y=0)
new_image, useful_list = crop_img(input_res, pil_img, crop_paste_x=width//2, crop_paste_y=0)
paste_x, paste_y, xmin, ymin, xmax, ymax, new_width, new_height = useful_list
layout_res = self.layout_model.predict(new_image)
for res in layout_res:
......@@ -197,12 +199,12 @@ class CustomPEKModel:
p7 = p7 - paste_x + xmin
p8 = p8 - paste_y + ymin
res['poly'] = [p1, p2, p3, p4, p5, p6, p7, p8]
else:
layout_res = self.layout_model.predict(image)
layout_cost = round(time.time() - layout_start, 2)
logger.info(f'layout detection time: {layout_cost}')
pil_img = Image.fromarray(image)
if self.apply_formula:
# 公式检测
mfd_start = time.time()
......
# Copyright (c) Opendatalab. All rights reserved.
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment