qurator-spk/eynollah
1
0
Fork 0
mirror of https://github.com/qurator-spk/eynollah.git synced 2025-10-27 07:44:12 +01:00
Code Issues Projects Releases Wiki Activity

Merge pull request #64 from mikegerber/feat/better-time-msgs

Browse source 
💄 Improve timing messages (Fixes #62)
This commit is contained in:
vahidrezanezhad 2022-03-03 07:04:01 -05:00 • committed by GitHub
commit c30d4d5c30
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 10 additions and 10 deletions
Download patch file Download diff file Expand all files Collapse all files

20
qurator/eynollah/eynollah.py
View file

@ -2115,7 +2115,7 @@ class Eynollah:
img_revised_tab2_d_rotated = img_revised_tab2_d_rotated.astype(np.int8) img_revised_tab2_d_rotated = img_revised_tab2_d_rotated.astype(np.int8)
img_revised_tab2_d_rotated = resize_image(img_revised_tab2_d_rotated, text_regions_p.shape[0], text_regions_p.shape[1]) img_revised_tab2_d_rotated = resize_image(img_revised_tab2_d_rotated, text_regions_p.shape[0], text_regions_p.shape[1])
self.logger.info("detecting boxes took %ss", str(time.time() - t1)) self.logger.info("detecting boxes took %.1fs", time.time() - t1)
if self.tables: if self.tables:
if np.abs(slope_deskew) < SLOPE_THRESHOLD: if np.abs(slope_deskew) < SLOPE_THRESHOLD:
@ -2306,37 +2306,37 @@ class Eynollah:
t0 = time.time() t0 = time.time()
img_res, is_image_enhanced, num_col_classifier, num_column_is_classified = self.run_enhancement() img_res, is_image_enhanced, num_col_classifier, num_column_is_classified = self.run_enhancement()
self.logger.info("Enhancing took %ss ", str(time.time() - t0)) self.logger.info("Enhancing took %.1fs ", time.time() - t0)
t1 = time.time() t1 = time.time()
text_regions_p_1 ,erosion_hurts, polygons_lines_xml = self.get_regions_from_xy_2models(img_res, is_image_enhanced, num_col_classifier) text_regions_p_1 ,erosion_hurts, polygons_lines_xml = self.get_regions_from_xy_2models(img_res, is_image_enhanced, num_col_classifier)
self.logger.info("Textregion detection took %ss ", str(time.time() - t1)) self.logger.info("Textregion detection took %.1fs ", time.time() - t1)
t1 = time.time() t1 = time.time()
num_col, num_col_classifier, img_only_regions, page_coord, image_page, mask_images, mask_lines, text_regions_p_1, cont_page, table_prediction = \ num_col, num_col_classifier, img_only_regions, page_coord, image_page, mask_images, mask_lines, text_regions_p_1, cont_page, table_prediction = \
self.run_graphics_and_columns(text_regions_p_1, num_col_classifier, num_column_is_classified, erosion_hurts) self.run_graphics_and_columns(text_regions_p_1, num_col_classifier, num_column_is_classified, erosion_hurts)
self.logger.info("Graphics detection took %ss ", str(time.time() - t1)) self.logger.info("Graphics detection took %.1fs ", time.time() - t1)
self.logger.info('cont_page %s', cont_page) self.logger.info('cont_page %s', cont_page)
if not num_col: if not num_col:
self.logger.info("No columns detected, outputting an empty PAGE-XML") self.logger.info("No columns detected, outputting an empty PAGE-XML")
pcgts = self.writer.build_pagexml_no_full_layout([], page_coord, [], [], [], [], [], [], [], [], [], [], cont_page, [], []) pcgts = self.writer.build_pagexml_no_full_layout([], page_coord, [], [], [], [], [], [], [], [], [], [], cont_page, [], [])
self.logger.info("Job done in %ss", str(time.time() - t1)) self.logger.info("Job done in %.1fs", time.time() - t1)
return pcgts return pcgts
t1 = time.time() t1 = time.time()
textline_mask_tot_ea = self.run_textline(image_page) textline_mask_tot_ea = self.run_textline(image_page)
self.logger.info("textline detection took %ss", str(time.time() - t1)) self.logger.info("textline detection took %.1fs", time.time() - t1)
t1 = time.time() t1 = time.time()
slope_deskew, slope_first = self.run_deskew(textline_mask_tot_ea) slope_deskew, slope_first = self.run_deskew(textline_mask_tot_ea)
self.logger.info("deskewing took %ss", str(time.time() - t1)) self.logger.info("deskewing took %.1fs", time.time() - t1)
t1 = time.time() t1 = time.time()
#plt.imshow(table_prediction) #plt.imshow(table_prediction)
#plt.show() #plt.show()
textline_mask_tot, text_regions_p, image_page_rotated = self.run_marginals(image_page, textline_mask_tot_ea, mask_images, mask_lines, num_col_classifier, slope_deskew, text_regions_p_1, table_prediction) textline_mask_tot, text_regions_p, image_page_rotated = self.run_marginals(image_page, textline_mask_tot_ea, mask_images, mask_lines, num_col_classifier, slope_deskew, text_regions_p_1, table_prediction)
self.logger.info("detection of marginals took %ss", str(time.time() - t1)) self.logger.info("detection of marginals took %.1fs", time.time() - t1)
t1 = time.time() t1 = time.time()
if not self.full_layout: if not self.full_layout:
polygons_of_images, img_revised_tab, text_regions_p_1_n, textline_mask_tot_d, regions_without_separators_d, boxes, boxes_d, polygons_of_marginals, contours_tables = self.run_boxes_no_full_layout(image_page, textline_mask_tot, text_regions_p, slope_deskew, num_col_classifier, table_prediction, erosion_hurts) polygons_of_images, img_revised_tab, text_regions_p_1_n, textline_mask_tot_d, regions_without_separators_d, boxes, boxes_d, polygons_of_marginals, contours_tables = self.run_boxes_no_full_layout(image_page, textline_mask_tot, text_regions_p, slope_deskew, num_col_classifier, table_prediction, erosion_hurts)
@ -2553,7 +2553,7 @@ class Eynollah:
order_text_new, id_of_texts_tot = self.do_order_of_regions(contours_only_text_parent_d_ordered, contours_only_text_parent_h_d_ordered, boxes_d, textline_mask_tot_d) order_text_new, id_of_texts_tot = self.do_order_of_regions(contours_only_text_parent_d_ordered, contours_only_text_parent_h_d_ordered, boxes_d, textline_mask_tot_d)
pcgts = self.writer.build_pagexml_full_layout(contours_only_text_parent, contours_only_text_parent_h, page_coord, order_text_new, id_of_texts_tot, all_found_texline_polygons, all_found_texline_polygons_h, all_box_coord, all_box_coord_h, polygons_of_images, contours_tables, polygons_of_drop_capitals, polygons_of_marginals, all_found_texline_polygons_marginals, all_box_coord_marginals, slopes, slopes_h, slopes_marginals, cont_page, polygons_lines_xml) pcgts = self.writer.build_pagexml_full_layout(contours_only_text_parent, contours_only_text_parent_h, page_coord, order_text_new, id_of_texts_tot, all_found_texline_polygons, all_found_texline_polygons_h, all_box_coord, all_box_coord_h, polygons_of_images, contours_tables, polygons_of_drop_capitals, polygons_of_marginals, all_found_texline_polygons_marginals, all_box_coord_marginals, slopes, slopes_h, slopes_marginals, cont_page, polygons_lines_xml)
self.logger.info("Job done in %ss", str(time.time() - t0)) self.logger.info("Job done in %.1fs", time.time() - t0)
return pcgts return pcgts
else: else:
contours_only_text_parent_h = None contours_only_text_parent_h = None
@ -2563,5 +2563,5 @@ class Eynollah:
contours_only_text_parent_d_ordered = list(np.array(contours_only_text_parent_d_ordered)[index_by_text_par_con]) contours_only_text_parent_d_ordered = list(np.array(contours_only_text_parent_d_ordered)[index_by_text_par_con])
order_text_new, id_of_texts_tot = self.do_order_of_regions(contours_only_text_parent_d_ordered, contours_only_text_parent_h, boxes_d, textline_mask_tot_d) order_text_new, id_of_texts_tot = self.do_order_of_regions(contours_only_text_parent_d_ordered, contours_only_text_parent_h, boxes_d, textline_mask_tot_d)
pcgts = self.writer.build_pagexml_no_full_layout(txt_con_org, page_coord, order_text_new, id_of_texts_tot, all_found_texline_polygons, all_box_coord, polygons_of_images, polygons_of_marginals, all_found_texline_polygons_marginals, all_box_coord_marginals, slopes, slopes_marginals, cont_page, polygons_lines_xml, contours_tables) pcgts = self.writer.build_pagexml_no_full_layout(txt_con_org, page_coord, order_text_new, id_of_texts_tot, all_found_texline_polygons, all_box_coord, polygons_of_images, polygons_of_marginals, all_found_texline_polygons_marginals, all_box_coord_marginals, slopes, slopes_marginals, cont_page, polygons_lines_xml, contours_tables)
self.logger.info("Job done in %ss", str(time.time() - t0)) self.logger.info("Job done in %.1fs", time.time() - t0)
return pcgts return pcgts