From a56988a35a528aba7cefd85e1a83257f598a5085 Mon Sep 17 00:00:00 2001 From: Robert Sachunsky Date: Sat, 11 Feb 2023 12:05:49 +0000 Subject: [PATCH] contours: numpy now needs dtype=object --- qurator/eynollah/eynollah.py | 10 +++++----- qurator/eynollah/utils/contour.py | 2 +- 2 files changed, 6 insertions(+), 6 deletions(-) diff --git a/qurator/eynollah/eynollah.py b/qurator/eynollah/eynollah.py index 301f750..c854b46 100644 --- a/qurator/eynollah/eynollah.py +++ b/qurator/eynollah/eynollah.py @@ -2367,7 +2367,7 @@ class Eynollah: areas_cnt_text_parent = [area for area in areas_cnt_text if area > min_con_area] index_con_parents = np.argsort(areas_cnt_text_parent) - contours_only_text_parent = list(np.array(contours_only_text_parent)[index_con_parents]) + contours_only_text_parent = list(np.array(contours_only_text_parent, dtype=object)[index_con_parents]) areas_cnt_text_parent = list(np.array(areas_cnt_text_parent)[index_con_parents]) cx_bigest_big, cy_biggest_big, _, _, _, _, _ = find_new_features_of_contours([contours_biggest]) @@ -2382,7 +2382,7 @@ class Eynollah: if len(areas_cnt_text_d)>0: contours_biggest_d = contours_only_text_parent_d[np.argmax(areas_cnt_text_d)] index_con_parents_d = np.argsort(areas_cnt_text_d) - contours_only_text_parent_d = list(np.array(contours_only_text_parent_d)[index_con_parents_d]) + contours_only_text_parent_d = list(np.array(contours_only_text_parent_d, dtype=object)[index_con_parents_d]) areas_cnt_text_d = list(np.array(areas_cnt_text_d)[index_con_parents_d]) cx_bigest_d_big, cy_biggest_d_big, _, _, _, _, _ = find_new_features_of_contours([contours_biggest_d]) @@ -2446,7 +2446,7 @@ class Eynollah: areas_cnt_text_parent = [area for area in areas_cnt_text if area > min_con_area] index_con_parents = np.argsort(areas_cnt_text_parent) - contours_only_text_parent = list(np.array(contours_only_text_parent)[index_con_parents]) + contours_only_text_parent = list(np.array(contours_only_text_parent, dtype=object)[index_con_parents]) areas_cnt_text_parent = list(np.array(areas_cnt_text_parent)[index_con_parents]) cx_bigest_big, cy_biggest_big, _, _, _, _, _ = find_new_features_of_contours([contours_biggest]) @@ -2473,7 +2473,7 @@ class Eynollah: K.clear_session() if self.full_layout: if np.abs(slope_deskew) >= SLOPE_THRESHOLD: - 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, dtype=object)[index_by_text_par_con]) text_regions_p, contours_only_text_parent, contours_only_text_parent_h, all_box_coord, all_box_coord_h, all_found_texline_polygons, all_found_texline_polygons_h, slopes, slopes_h, contours_only_text_parent_d_ordered, contours_only_text_parent_h_d_ordered = check_any_text_region_in_model_one_is_main_or_header(text_regions_p, regions_fully, contours_only_text_parent, all_box_coord, all_found_texline_polygons, slopes, contours_only_text_parent_d_ordered) else: contours_only_text_parent_d_ordered = None @@ -2566,7 +2566,7 @@ class Eynollah: if np.abs(slope_deskew) < SLOPE_THRESHOLD: order_text_new, id_of_texts_tot = self.do_order_of_regions(contours_only_text_parent, contours_only_text_parent_h, boxes, textline_mask_tot) else: - 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, dtype=object)[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) 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 %.1fs", time.time() - t0) diff --git a/qurator/eynollah/utils/contour.py b/qurator/eynollah/utils/contour.py index 6b81391..d8a8af9 100644 --- a/qurator/eynollah/utils/contour.py +++ b/qurator/eynollah/utils/contour.py @@ -19,7 +19,7 @@ def contours_in_same_horizon(cy_main_hor): list_h.append(i) if len(list_h) > 1: all_args.append(list(set(list_h))) - return np.unique(all_args) + return np.unique(np.array(all_args, dtype=object)) def find_contours_mean_y_diff(contours_main): M_main = [cv2.moments(contours_main[j]) for j in range(len(contours_main))]