qurator-spk/eynollah
1
0
Fork 0
mirror of https://github.com/qurator-spk/eynollah.git synced 2026-02-20 16:32:03 +01:00
Code Issues Projects Releases Wiki Activity

training.generate_gt: for RO, skip files if regionRefs are missing

Browse source
This commit is contained in:
Robert Sachunsky 2026-02-05 14:53:26 +01:00
parent 5d0c26b629
commit b1633dfc7c
1 changed files with 11 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

16
src/eynollah/training/generate_gt_for_training.py
View file

@ -205,14 +205,20 @@ def machine_based_reading_order(dir_xml, dir_out_modal_image, dir_out_classes, i
img_header_and_sep = np.zeros((y_len,x_len), dtype='uint8')
for j in range(len(cy_main)):
img_header_and_sep[int(y_max_main[j]):int(y_max_main[j])+12,int(x_min_main[j]):int(x_max_main[j]) ] = 1
img_header_and_sep[int(y_max_main[j]):int(y_max_main[j])+12,
int(x_min_main[j]):int(x_max_main[j]) ] = 1
texts_corr_order_index = [index_tot_regions[tot_region_ref.index(i)] for i in id_all_text ]
texts_corr_order_index_int = [int(x) for x in texts_corr_order_index]
try:
texts_corr_order_index_int = [int(index_tot_regions[tot_region_ref.index(i)])
for i in id_all_text]
except ValueError as e:
print("incomplete ReadingOrder in", xml_file, "- skipping:", str(e))
continue
co_text_all, texts_corr_order_index_int, regions_ar_less_than_early_min = filter_contours_area_of_image(img_poly, co_text_all, texts_corr_order_index_int, max_area, min_area, min_area_early)
co_text_all, texts_corr_order_index_int, regions_ar_less_than_early_min = \
filter_contours_area_of_image(img_poly, co_text_all, texts_corr_order_index_int,
max_area, min_area, min_area_early)
arg_array = np.array(range(len(texts_corr_order_index_int)))