qurator-spk/eynollah
1
0
Fork 0
mirror of https://github.com/qurator-spk/eynollah.git synced 2025-06-08 11:49:55 +02:00
Code Issues Projects Releases Wiki Activity

switch from (ad-hoc) mp.Pool to (attribute) concurrent.futures.ProcessPoolExecutor

Browse source
This commit is contained in:
Robert Sachunsky 2024-12-11 12:18:29 +00:00
parent 68456ea002
commit 7e9ee90e6e
3 changed files with 91 additions and 95 deletions
Download patch file Download diff file Expand all files Collapse all files

46
src/eynollah/eynollah.py
View file

@ -13,7 +13,8 @@ import time
import warnings import warnings
from functools import partial from functools import partial
from pathlib import Path from pathlib import Path
from multiprocessing import Pool, cpu_count from multiprocessing import cpu_count
from concurrent.futures import ProcessPoolExecutor
import gc import gc
from ocrd_utils import getLogger from ocrd_utils import getLogger
import cv2 import cv2
@ -251,6 +252,8 @@ class Eynollah:
textline_light = self.textline_light, textline_light = self.textline_light,
pcgts=pcgts) pcgts=pcgts)
self.logger = logger if logger else getLogger('eynollah') self.logger = logger if logger else getLogger('eynollah')
# for parallelization of CPU-intensive tasks:
self.executor = ProcessPoolExecutor(max_workers=cpu_count())
self.dir_models = dir_models self.dir_models = dir_models
self.model_dir_of_enhancement = dir_models + "/eynollah-enhancement_20210425" self.model_dir_of_enhancement = dir_models + "/eynollah-enhancement_20210425"
self.model_dir_of_binarization = dir_models + "/eynollah-binarization_20210425" self.model_dir_of_binarization = dir_models + "/eynollah-binarization_20210425"
@ -1518,21 +1521,15 @@ class Eynollah:
if not len(contours): if not len(contours):
return [], [], [], [], [], [], [] return [], [], [], [], [], [], []
self.logger.debug("enter get_slopes_and_deskew_new_light") self.logger.debug("enter get_slopes_and_deskew_new_light")
if len(contours)>15: results = self.executor.map(partial(do_work_of_slopes_new_light,
num_cores = cpu_count()
else:
num_cores = 1
with Pool(processes=num_cores) as pool:
results = pool.starmap(
partial(do_work_of_slopes_new_light,
textline_mask_tot_ea=textline_mask_tot, textline_mask_tot_ea=textline_mask_tot,
image_page_rotated=image_page_rotated, image_page_rotated=image_page_rotated,
slope_deskew=slope_deskew, slope_deskew=slope_deskew,
logger=self.logger,
MAX_SLOPE=MAX_SLOPE, MAX_SLOPE=MAX_SLOPE,
KERNEL=KERNEL, KERNEL=KERNEL,
logger=self.logger,
plotter=self.plotter,), plotter=self.plotter,),
zip(boxes, contours, contours_par, range(len(contours_par)))) boxes, contours, contours_par, range(len(contours_par)))
#textline_polygons, boxes, text_regions, text_regions_par, box_coord, index_text_con, slopes = zip(*results) #textline_polygons, boxes, text_regions, text_regions_par, box_coord, index_text_con, slopes = zip(*results)
self.logger.debug("exit get_slopes_and_deskew_new_light") self.logger.debug("exit get_slopes_and_deskew_new_light")
return tuple(zip(*results)) return tuple(zip(*results))
@ -1541,18 +1538,15 @@ class Eynollah:
if not len(contours): if not len(contours):
return [], [], [], [], [], [], [] return [], [], [], [], [], [], []
self.logger.debug("enter get_slopes_and_deskew_new") self.logger.debug("enter get_slopes_and_deskew_new")
num_cores = cpu_count() results = self.executor.map(partial(do_work_of_slopes_new,
with Pool(processes=num_cores) as pool:
results = pool.starmap(
partial(do_work_of_slopes_new,
textline_mask_tot_ea=textline_mask_tot, textline_mask_tot_ea=textline_mask_tot,
image_page_rotated=image_page_rotated, image_page_rotated=image_page_rotated,
slope_deskew=slope_deskew, slope_deskew=slope_deskew,
logger=self.logger,
MAX_SLOPE=MAX_SLOPE, MAX_SLOPE=MAX_SLOPE,
KERNEL=KERNEL, KERNEL=KERNEL,
logger=self.logger,
plotter=self.plotter,), plotter=self.plotter,),
zip(boxes, contours, contours_par, range(len(contours_par)))) boxes, contours, contours_par, range(len(contours_par)))
#textline_polygons, boxes, text_regions, text_regions_par, box_coord, index_text_con, slopes = zip(*results) #textline_polygons, boxes, text_regions, text_regions_par, box_coord, index_text_con, slopes = zip(*results)
self.logger.debug("exit get_slopes_and_deskew_new") self.logger.debug("exit get_slopes_and_deskew_new")
return tuple(zip(*results)) return tuple(zip(*results))
@ -1561,21 +1555,18 @@ class Eynollah:
if not len(contours): if not len(contours):
return [], [], [], [], [], [], [] return [], [], [], [], [], [], []
self.logger.debug("enter get_slopes_and_deskew_new_curved") self.logger.debug("enter get_slopes_and_deskew_new_curved")
num_cores = cpu_count() results = self.executor.map(partial(do_work_of_slopes_new_curved,
with Pool(processes=num_cores) as pool:
results = pool.starmap(
partial(do_work_of_slopes_new_curved,
textline_mask_tot_ea=textline_mask_tot, textline_mask_tot_ea=textline_mask_tot,
image_page_rotated=image_page_rotated, image_page_rotated=image_page_rotated,
mask_texts_only=mask_texts_only, mask_texts_only=mask_texts_only,
num_col=num_col, num_col=num_col,
scale_par=scale_par, scale_par=scale_par,
slope_deskew=slope_deskew, slope_deskew=slope_deskew,
logger=self.logger,
MAX_SLOPE=MAX_SLOPE, MAX_SLOPE=MAX_SLOPE,
KERNEL=KERNEL, KERNEL=KERNEL,
logger=self.logger,
plotter=self.plotter,), plotter=self.plotter,),
zip(boxes, contours, contours_par, range(len(contours_par)))) boxes, contours, contours_par, range(len(contours_par)))
#textline_polygons, boxes, text_regions, text_regions_par, box_coord, index_text_con, slopes = zip(*results) #textline_polygons, boxes, text_regions, text_regions_par, box_coord, index_text_con, slopes = zip(*results)
self.logger.debug("exit get_slopes_and_deskew_new_curved") self.logger.debug("exit get_slopes_and_deskew_new_curved")
return tuple(zip(*results)) return tuple(zip(*results))
@ -1643,7 +1634,8 @@ class Eynollah:
y_diff_mean = find_contours_mean_y_diff(textline_con_fil) y_diff_mean = find_contours_mean_y_diff(textline_con_fil)
sigma_des = max(1, int(y_diff_mean * (4.0 / 40.0))) sigma_des = max(1, int(y_diff_mean * (4.0 / 40.0)))
crop_img[crop_img > 0] = 1 crop_img[crop_img > 0] = 1
slope_corresponding_textregion = return_deskew_slop(crop_img, sigma_des, plotter=self.plotter) slope_corresponding_textregion = return_deskew_slop(crop_img, sigma_des,
map=self.executor.map, logger=self.logger, plotter=self.plotter)
except Exception as why: except Exception as why:
self.logger.error(why) self.logger.error(why)
slope_corresponding_textregion = MAX_SLOPE slope_corresponding_textregion = MAX_SLOPE
@ -2932,10 +2924,8 @@ class Eynollah:
def run_deskew(self, textline_mask_tot_ea): def run_deskew(self, textline_mask_tot_ea):
#print(textline_mask_tot_ea.shape, 'textline_mask_tot_ea deskew') #print(textline_mask_tot_ea.shape, 'textline_mask_tot_ea deskew')
sigma = 2 slope_deskew = return_deskew_slop(cv2.erode(textline_mask_tot_ea, KERNEL, iterations=2), 2, 30, True,
main_page_deskew = True map=self.executor.map, logger=self.logger, plotter=self.plotter)
n_total_angles = 30
slope_deskew = return_deskew_slop(cv2.erode(textline_mask_tot_ea, KERNEL, iterations=2), sigma, n_total_angles, main_page_deskew, plotter=self.plotter)
slope_first = 0 slope_first = 0
if self.plotter: if self.plotter:
@ -4748,7 +4738,7 @@ class Eynollah:
contours_only_text_parent = self.dilate_textregions_contours(contours_only_text_parent) contours_only_text_parent = self.dilate_textregions_contours(contours_only_text_parent)
contours_only_text_parent = self.filter_contours_inside_a_bigger_one(contours_only_text_parent, text_only, marginal_cnts=polygons_of_marginals) contours_only_text_parent = self.filter_contours_inside_a_bigger_one(contours_only_text_parent, text_only, marginal_cnts=polygons_of_marginals)
#print("text region early 3.5 in %.1fs", time.time() - t0) #print("text region early 3.5 in %.1fs", time.time() - t0)
txt_con_org = get_textregion_contours_in_org_image_light(contours_only_text_parent, self.image, slope_first) txt_con_org = get_textregion_contours_in_org_image_light(contours_only_text_parent, self.image, slope_first, map=self.executor.map)
#txt_con_org = self.dilate_textregions_contours(txt_con_org) #txt_con_org = self.dilate_textregions_contours(txt_con_org)
#contours_only_text_parent = self.dilate_textregions_contours(contours_only_text_parent) #contours_only_text_parent = self.dilate_textregions_contours(contours_only_text_parent)
else: else:

19
src/eynollah/utils/contour.py
View file

@ -1,5 +1,4 @@
from functools import partial from functools import partial
from multiprocessing import cpu_count, Pool
import cv2 import cv2
import numpy as np import numpy as np
from shapely import geometry from shapely import geometry
@ -162,17 +161,14 @@ def do_work_of_contours_in_image(contour, index_r_con, img, slope_first):
return cont_int[0], index_r_con return cont_int[0], index_r_con
def get_textregion_contours_in_org_image_multi(cnts, img, slope_first): def get_textregion_contours_in_org_image_multi(cnts, img, slope_first, map=map):
if not len(cnts): if not len(cnts):
return [], [] return [], []
num_cores = cpu_count() results = map(partial(do_work_of_contours_in_image,
with Pool(processes=num_cores) as pool:
results = pool.starmap(
partial(do_work_of_contours_in_image,
img=img, img=img,
slope_first=slope_first, slope_first=slope_first,
), ),
zip(cnts, range(len(cnts)))) cnts, range(len(cnts)))
return tuple(zip(*results)) return tuple(zip(*results))
def get_textregion_contours_in_org_image(cnts, img, slope_first): def get_textregion_contours_in_org_image(cnts, img, slope_first):
@ -252,21 +248,18 @@ def do_back_rotation_and_get_cnt_back(contour_par, index_r_con, img, slope_first
# print(np.shape(cont_int[0])) # print(np.shape(cont_int[0]))
return cont_int[0], index_r_con return cont_int[0], index_r_con
def get_textregion_contours_in_org_image_light(cnts, img, slope_first): def get_textregion_contours_in_org_image_light(cnts, img, slope_first, map=map):
if not len(cnts): if not len(cnts):
return [] return []
img = cv2.resize(img, (int(img.shape[1]/6), int(img.shape[0]/6)), interpolation=cv2.INTER_NEAREST) img = cv2.resize(img, (int(img.shape[1]/6), int(img.shape[0]/6)), interpolation=cv2.INTER_NEAREST)
##cnts = list( (np.array(cnts)/2).astype(np.int16) ) ##cnts = list( (np.array(cnts)/2).astype(np.int16) )
#cnts = cnts/2 #cnts = cnts/2
cnts = [(i/6).astype(np.int) for i in cnts] cnts = [(i/6).astype(np.int) for i in cnts]
num_cores = cpu_count() results = map(partial(do_back_rotation_and_get_cnt_back,
with Pool(processes=num_cores) as pool:
results = pool.starmap(
partial(do_back_rotation_and_get_cnt_back,
img=img, img=img,
slope_first=slope_first, slope_first=slope_first,
), ),
zip(cnts, range(len(cnts)))) cnts, range(len(cnts)))
contours, indexes = tuple(zip(*results)) contours, indexes = tuple(zip(*results))
return [i*6 for i in contours] return [i*6 for i in contours]

67
src/eynollah/utils/separate_lines.py
View file

@ -1,6 +1,6 @@
import os import os
from logging import getLogger
from functools import partial from functools import partial
from multiprocessing import Pool, cpu_count
import numpy as np import numpy as np
import cv2 import cv2
from scipy.signal import find_peaks from scipy.signal import find_peaks
@ -1464,7 +1464,9 @@ def textline_contours_postprocessing(textline_mask, slope, contour_text_interest
return contours_rotated_clean return contours_rotated_clean
def separate_lines_new2(img_path, thetha, num_col, slope_region, plotter=None): def separate_lines_new2(img_path, thetha, num_col, slope_region, logger=None, plotter=None):
if logger is None:
logger = getLogger(__package__)
if num_col == 1: if num_col == 1:
num_patches = int(img_path.shape[1] / 200.0) num_patches = int(img_path.shape[1] / 200.0)
@ -1572,18 +1574,20 @@ def separate_lines_new2(img_path, thetha, num_col, slope_region, plotter=None):
# plt.show() # plt.show()
return img_patch_ineterst_revised return img_patch_ineterst_revised
def do_image_rotation(angle, img, sigma_des): def do_image_rotation(angle, img, sigma_des, logger=None):
print(f"rotating image by {angle}") if logger is None:
logger = getLogger(__package__)
img_rot = rotate_image(img, angle) img_rot = rotate_image(img, angle)
img_rot[img_rot!=0] = 1 img_rot[img_rot!=0] = 1
try: try:
var = find_num_col_deskew(img_rot, sigma_des, 20.3) var = find_num_col_deskew(img_rot, sigma_des, 20.3)
except: except:
logger.exception("cannot determine variance for angle %.2f°", angle)
var = 0 var = 0
return var return var
def return_deskew_slop(img_patch_org, sigma_des,n_tot_angles=100, main_page=False, plotter=None): def return_deskew_slop(img_patch_org, sigma_des,n_tot_angles=100,
num_cores = cpu_count() main_page=False, logger=None, plotter=None, map=map):
if main_page and plotter: if main_page and plotter:
plotter.save_plot_of_textline_density(img_patch_org) plotter.save_plot_of_textline_density(img_patch_org)
@ -1615,16 +1619,16 @@ def return_deskew_slop(img_patch_org, sigma_des,n_tot_angles=100, main_page=Fals
#plt.imshow(img_resized) #plt.imshow(img_resized)
#plt.show() #plt.show()
angles = np.array([-45, 0, 45, 90,]) angles = np.array([-45, 0, 45, 90,])
angle = get_smallest_skew(img_resized, sigma_des, angles, num_cores=num_cores, plotter=plotter) angle = get_smallest_skew(img_resized, sigma_des, angles, map=map, logger=logger, plotter=plotter)
angles = np.linspace(angle - 22.5, angle + 22.5, n_tot_angles) angles = np.linspace(angle - 22.5, angle + 22.5, n_tot_angles)
angle = get_smallest_skew(img_resized, sigma_des, angles, num_cores=num_cores, plotter=plotter) angle = get_smallest_skew(img_resized, sigma_des, angles, map=map, logger=logger, plotter=plotter)
elif main_page: elif main_page:
#plt.imshow(img_resized) #plt.imshow(img_resized)
#plt.show() #plt.show()
angles = np.linspace(-12, 12, n_tot_angles)#np.array([0 , 45 , 90 , -45]) angles = np.linspace(-12, 12, n_tot_angles)#np.array([0 , 45 , 90 , -45])
angle = get_smallest_skew(img_resized, sigma_des, angles, num_cores=num_cores, plotter=plotter) angle = get_smallest_skew(img_resized, sigma_des, angles, map=map, logger=logger, plotter=plotter)
early_slope_edge=11 early_slope_edge=11
if abs(angle) > early_slope_edge: if abs(angle) > early_slope_edge:
@ -1632,11 +1636,11 @@ def return_deskew_slop(img_patch_org, sigma_des,n_tot_angles=100, main_page=Fals
angles = np.linspace(-90, -12, n_tot_angles) angles = np.linspace(-90, -12, n_tot_angles)
else: else:
angles = np.linspace(90, 12, n_tot_angles) angles = np.linspace(90, 12, n_tot_angles)
angle = get_smallest_skew(img_resized, sigma_des, angles, num_cores=num_cores, plotter=plotter) angle = get_smallest_skew(img_resized, sigma_des, angles, map=map, logger=logger, plotter=plotter)
else: else:
angles = np.linspace(-25, 25, int(0.5 * n_tot_angles) + 10) angles = np.linspace(-25, 25, int(0.5 * n_tot_angles) + 10)
angle = get_smallest_skew(img_resized, sigma_des, angles, num_cores=num_cores, plotter=plotter) angle = get_smallest_skew(img_resized, sigma_des, angles, map=map, logger=logger, plotter=plotter)
early_slope_edge=22 early_slope_edge=22
if abs(angle) > early_slope_edge: if abs(angle) > early_slope_edge:
@ -1644,30 +1648,35 @@ def return_deskew_slop(img_patch_org, sigma_des,n_tot_angles=100, main_page=Fals
angles = np.linspace(-90, -25, int(0.5 * n_tot_angles) + 10) angles = np.linspace(-90, -25, int(0.5 * n_tot_angles) + 10)
else: else:
angles = np.linspace(90, 25, int(0.5 * n_tot_angles) + 10) angles = np.linspace(90, 25, int(0.5 * n_tot_angles) + 10)
angle = get_smallest_skew(img_resized, sigma_des, angles, num_cores=num_cores, plotter=plotter) angle = get_smallest_skew(img_resized, sigma_des, angles, map=map, logger=logger, plotter=plotter)
return angle return angle
def get_smallest_skew(img, sigma_des, angles, num_cores=1, plotter=None): def get_smallest_skew(img, sigma_des, angles, logger=None, plotter=None, map=map):
with Pool(processes=num_cores) as pool: if logger is None:
results = pool.map(partial(do_image_rotation, img=img, sigma_des=sigma_des), angles) logger = getLogger(__package__)
results = list(map(partial(do_image_rotation, img=img, sigma_des=sigma_des, logger=logger), angles))
if plotter: if plotter:
plotter.save_plot_of_rotation_angle(angles, results) plotter.save_plot_of_rotation_angle(angles, results)
try: try:
var_res = np.array(results) var_res = np.array(results)
assert var_res.any()
angle = angles[np.argmax(var_res)] angle = angles[np.argmax(var_res)]
except: except:
logger.exception("cannot determine best angle among %s", str(angles))
angle = 0 angle = 0
return angle return angle
def do_work_of_slopes_new( def do_work_of_slopes_new(
box_text, contour, contour_par, index_r_con, box_text, contour, contour_par, index_r_con,
textline_mask_tot_ea, image_page_rotated, slope_deskew, textline_mask_tot_ea, image_page_rotated, slope_deskew,
logger, MAX_SLOPE=999, KERNEL=None, plotter=None logger=None, MAX_SLOPE=999, KERNEL=None, plotter=None
): ):
logger.debug('enter do_work_of_slopes_new')
if KERNEL is None: if KERNEL is None:
KERNEL = np.ones((5, 5), np.uint8) KERNEL = np.ones((5, 5), np.uint8)
if logger is None:
logger = getLogger(__package__)
logger.debug('enter do_work_of_slopes_new')
x, y, w, h = box_text x, y, w, h = box_text
_, crop_coor = crop_image_inside_box(box_text, image_page_rotated) _, crop_coor = crop_image_inside_box(box_text, image_page_rotated)
@ -1693,11 +1702,11 @@ def do_work_of_slopes_new(
else: else:
sigma_des = max(1, int(y_diff_mean * (4.0 / 40.0))) sigma_des = max(1, int(y_diff_mean * (4.0 / 40.0)))
img_int_p[img_int_p > 0] = 1 img_int_p[img_int_p > 0] = 1
slope_for_all = return_deskew_slop(img_int_p, sigma_des, plotter=plotter) slope_for_all = return_deskew_slop(img_int_p, sigma_des, logger=logger, plotter=plotter)
if abs(slope_for_all) <= 0.5: if abs(slope_for_all) <= 0.5:
slope_for_all = slope_deskew slope_for_all = slope_deskew
except Exception as why: except:
logger.error(why) logger.exception("cannot determine angle of contours")
slope_for_all = MAX_SLOPE slope_for_all = MAX_SLOPE
if slope_for_all == MAX_SLOPE: if slope_for_all == MAX_SLOPE:
@ -1728,11 +1737,13 @@ def do_work_of_slopes_new(
def do_work_of_slopes_new_curved( def do_work_of_slopes_new_curved(
box_text, contour, contour_par, index_r_con, box_text, contour, contour_par, index_r_con,
textline_mask_tot_ea, image_page_rotated, mask_texts_only, num_col, scale_par, slope_deskew, textline_mask_tot_ea, image_page_rotated, mask_texts_only, num_col, scale_par, slope_deskew,
logger, MAX_SLOPE=999, KERNEL=None, plotter=None logger=None, MAX_SLOPE=999, KERNEL=None, plotter=None
): ):
logger.debug("enter do_work_of_slopes_new_curved")
if KERNEL is None: if KERNEL is None:
KERNEL = np.ones((5, 5), np.uint8) KERNEL = np.ones((5, 5), np.uint8)
if logger is None:
logger = getLogger(__package__)
logger.debug("enter do_work_of_slopes_new_curved")
x, y, w, h = box_text x, y, w, h = box_text
all_text_region_raw = textline_mask_tot_ea[y: y + h, x: x + w].astype(np.uint8) all_text_region_raw = textline_mask_tot_ea[y: y + h, x: x + w].astype(np.uint8)
@ -1755,11 +1766,11 @@ def do_work_of_slopes_new_curved(
else: else:
sigma_des = max(1, int(y_diff_mean * (4.0 / 40.0))) sigma_des = max(1, int(y_diff_mean * (4.0 / 40.0)))
img_int_p[img_int_p > 0] = 1 img_int_p[img_int_p > 0] = 1
slope_for_all = return_deskew_slop(img_int_p, sigma_des, plotter=plotter) slope_for_all = return_deskew_slop(img_int_p, sigma_des, logger=logger, plotter=plotter)
if abs(slope_for_all) < 0.5: if abs(slope_for_all) < 0.5:
slope_for_all = slope_deskew slope_for_all = slope_deskew
except Exception as why: except:
logger.error(why) logger.exception("cannot determine angle of contours")
slope_for_all = MAX_SLOPE slope_for_all = MAX_SLOPE
if slope_for_all == MAX_SLOPE: if slope_for_all == MAX_SLOPE:
@ -1778,7 +1789,7 @@ def do_work_of_slopes_new_curved(
# print(slope_for_all,'slope_for_all') # print(slope_for_all,'slope_for_all')
textline_rotated_separated = separate_lines_new2(textline_biggest_region[y: y+h, x: x+w], 0, num_col, slope_for_all, textline_rotated_separated = separate_lines_new2(textline_biggest_region[y: y+h, x: x+w], 0, num_col, slope_for_all,
plotter=plotter) logger=logger, plotter=plotter)
# new line added # new line added
##print(np.shape(textline_rotated_separated),np.shape(mask_biggest)) ##print(np.shape(textline_rotated_separated),np.shape(mask_biggest))
@ -1818,8 +1829,10 @@ def do_work_of_slopes_new_curved(
def do_work_of_slopes_new_light( def do_work_of_slopes_new_light(
box_text, contour, contour_par, index_r_con, box_text, contour, contour_par, index_r_con,
textline_mask_tot_ea, image_page_rotated, slope_deskew, textline_mask_tot_ea, image_page_rotated, slope_deskew,
logger logger=None
): ):
if logger is None:
logger = getLogger(__package__)
logger.debug('enter do_work_of_slopes_new_light') logger.debug('enter do_work_of_slopes_new_light')
x, y, w, h = box_text x, y, w, h = box_text