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.gt_gen_utils: improve XML→img path mapping…

Browse source 
when matching files in `dir_images` by XML path name stem,
 * use `dict` instead of `list` to assign reliably
 * filter out `.xml` files (so input directories can be mixed)
 * show informative warnings for files which cannot be matched
This commit is contained in:
Robert Sachunsky 2026-01-28 13:28:03 +01:00
parent eb92760f73
commit acda9c84ee
1 changed files with 18 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

21
src/eynollah/training/gt_gen_utils.py
View file

@ -627,7 +627,10 @@ def get_images_of_ground_truth(gt_list, dir_in, output_dir, output_type, config_
if dir_images:
ls_org_imgs = os.listdir(dir_images)
ls_org_imgs_stem = [os.path.splitext(item)[0] for item in ls_org_imgs]
ls_org_imgs = {os.path.splitext(item)[0]: item
for item in ls_org_imgs
if not item.endswith('.xml')}
for index in tqdm(range(len(gt_list))):
#try:
print(gt_list[index])
@ -802,7 +805,13 @@ def get_images_of_ground_truth(gt_list, dir_in, output_dir, output_type, config_
cv2.imwrite(os.path.join(output_dir, xml_file_stem + '.png'), img_poly)
if dir_images:
org_image_name = ls_org_imgs[ls_org_imgs_stem.index(xml_file_stem)]
org_image_name = ls_org_imgs[xml_file_stem]
if not org_image_name:
print("image file for XML stem", xml_file_stem, "is missing")
continue
if not os.path.isfile(os.path.join(dir_images, org_image_name)):
print("image file for XML stem", xml_file_stem, "is not readable")
continue
img_org = cv2.imread(os.path.join(dir_images, org_image_name))
if printspace and config_params['use_case']!='printspace':
@ -1266,7 +1275,13 @@ def get_images_of_ground_truth(gt_list, dir_in, output_dir, output_type, config_
if dir_images:
org_image_name = ls_org_imgs[ls_org_imgs_stem.index(xml_file_stem)]
org_image_name = ls_org_imgs[xml_file_stem]
if not org_image_name:
print("image file for XML stem", xml_file_stem, "is missing")
continue
if not os.path.isfile(os.path.join(dir_images, org_image_name)):
print("image file for XML stem", xml_file_stem, "is not readable")
continue
img_org = cv2.imread(os.path.join(dir_images, org_image_name))
if printspace: