resolved merge conflicts

OCR-D · Oct 31, 2019 · 44247ab · 44247ab
2 parents 6bf4020 + 26faa50
commit 44247ab
Show file tree

Hide file tree

Showing 4 changed files with 3 additions and 134 deletions.
diff --git a/ocrd_anybaseocr/cli/ocrd_anybaseocr_binarize.py b/ocrd_anybaseocr/cli/ocrd_anybaseocr_binarize.py
@@ -108,9 +108,6 @@ def process(self):
 
         for (n, input_file) in enumerate(self.input_files):            
             page_id = input_file.pageId or input_file.ID
-#             if input_file.pageId is None:
-#                 continue
-#             page_id = input_file.pageId
 
             LOG.info("INPUT FILE %i / %s", n, page_id)
             pcgts = page_from_file(self.workspace.download_file(input_file))
@@ -159,7 +156,6 @@ def _process_segment(self,page_image, page, page_xywh, page_id, input_file, n):
         if len(raw.shape) > 2:
             raw = np.mean(raw, 2)
         raw = raw.astype("float64")
-
         # perform image normalization
         image = raw-amin(raw)
         if amax(image) == amin(image):
@@ -255,3 +251,4 @@ def _process_segment(self,page_image, page, page_xywh, page_id, input_file, n):
                                    file_grp=self.image_grp
             )     
         page.add_AlternativeImage(AlternativeImageType(filename=file_path, comments=page_xywh['features']))
+
diff --git a/ocrd_anybaseocr/cli/ocrd_anybaseocr_cropping.py b/ocrd_anybaseocr/cli/ocrd_anybaseocr_cropping.py
@@ -424,12 +424,8 @@ def process(self):
             self.image_grp = FALLBACK_IMAGE_GRP
             LOG.info("No output file group for images specified, falling back to '%s'", FALLBACK_IMAGE_GRP)
         oplevel = self.parameter['operation_level']
-
         for (n, input_file) in enumerate(self.input_files):
             page_id = input_file.pageId or input_file.ID 
-            #if input_file.mimetype =="image/png":
-            #    continue
-            #page_id = input_file.pageId  
 
             LOG.info("INPUT FILE %i / %s", n, page_id)
 
@@ -463,6 +459,7 @@ def process(self):
                 LOG.warning('Operation level %s, but should be "page".', oplevel)
                 break
             file_id = input_file.ID.replace(self.input_file_grp, self.output_file_grp)
+
             # Use input_file's basename for the new file -
             # this way the files retain the same basenames:
             if file_id == input_file.ID:
@@ -500,7 +497,6 @@ def _process_segment(self,page_image, page, page_xywh, page_id, input_file, n):
             img_array_rr)
         self.parameter['colSeparator'] = int(
             width * self.parameter['colSeparator'])
-
         if len(textarea) > 1:
             textarea = self.crop_area(
                 textarea, img_array_bin, img_array_rr_ta)
@@ -517,7 +513,6 @@ def _process_segment(self,page_image, page, page_xywh, page_id, input_file, n):
             y1 = y1-40 if y1 > 40 else 0
             y2 = y2+40 if y2 < height-40 else height
 
-            #self.save_pf(base, [x1, y1, x2, y2])                
             min_x, min_y, max_x, max_y = textarea[0]
         else:
             min_x, min_y, max_x, max_y = self.select_borderLine(
@@ -540,3 +535,4 @@ def _process_segment(self,page_image, page, page_xywh, page_id, input_file, n):
                                file_grp=self.image_grp
         )        
         page.add_AlternativeImage(AlternativeImageType(filename=file_path, comments=page_xywh['features']))
+
diff --git a/ocrd_anybaseocr/cli/ocrd_anybaseocr_deskew.py b/ocrd_anybaseocr/cli/ocrd_anybaseocr_deskew.py
@@ -95,11 +95,7 @@ def process(self):
         oplevel = self.parameter['operation_level']
 
         for (n, input_file) in enumerate(self.input_files):
-            #file_id = input_file.ID.replace(self.input_file_grp, self.image_grp)
             page_id = input_file.pageId or input_file.ID 
-            #if input_file.mimetype !="image/png":
-            #    continue
-            #page_id = input_file.pageId
 
             LOG.info("INPUT FILE %i / %s", n, page_id)
             pcgts = page_from_file(self.workspace.download_file(input_file))

diff --git a/ocrd_anybaseocr/cli/ocrd_anybaseocr_dewarp.py b/ocrd_anybaseocr/cli/ocrd_anybaseocr_dewarp.py
@@ -168,124 +168,4 @@ def _process_segment(self, model, dataset, page, page_xywh, page_id, input_file,
                 )     
             page.add_AlternativeImage(AlternativeImageType(filename=file_path, comments=page_xywh['features']))
 
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
 
-
-
-
-
-# import torch
-# import sys
-# import os
-# import shutil
-
-# from ..constants import OCRD_TOOL
-
-# from ocrd import Processor
-
-# from ocrd_models.ocrd_page import parse
-# from ocrd_utils import getLogger, concat_padded
-# from ocrd_modelfactory import page_from_file
-# from ocrd_models.ocrd_page import to_xml,parse
-# import shutil
-
-# from pathlib import Path
-# from PIL import Image
-# import ocrolib
-
-# TOOL = 'ocrd-anybaseocr-dewarp'
-# LOG = getLogger('OcrdAnybaseocrDewarper')
-
-# class OcrdAnybaseocrDewarper(Processor):
-
-#     def __init__(self, *args, **kwargs):
-#         kwargs['ocrd_tool'] = OCRD_TOOL['tools'][TOOL]
-#         kwargs['version'] = OCRD_TOOL['version']        
-#         super(OcrdAnybaseocrDewarper, self).__init__(*args, **kwargs)
-
-#     def crop_image(self, image_path, crop_region):
-#         img = Image.open(image_path)
-#         cropped = img.crop(crop_region)
-#         return cropped
-
-#     def process(self):        
-#         if not torch.cuda.is_available():
-#             LOG.error("Your system has no CUDA installed. No GPU detected.")
-#             sys.exit(1)
-
-#         path = Path(self.parameter['pix2pixHD']).absolute()
-
-#         if not Path(path).is_dir():
-#             LOG.error("""\
-#                 NVIDIA's pix2pixHD was not found at '%s'. Make sure the `pix2pixHD` parameter 
-#                 in params.json points to the local path to the cloned pix2pixHD repository.
-
-#                 pix2pixHD can be downloaded from https://github.com/NVIDIA/pix2pixHD
-#                 """ % path)
-#             sys.exit(1)
-
-
-#         for (_, input_file) in enumerate(self.input_files):
-#             local_input_file = self.workspace.download_file(input_file)
-#             pcgts = parse(local_input_file.url, silence=True)
-#             image_coords = pcgts.get_Page().get_Border().get_Coords().points.split()
-#             fname = pcgts.get_Page().imageFilename
-#             LOG.info("INPUT FILE %s", fname)
-
-#             # Get page Co-ordinates
-#             min_x, min_y = image_coords[0].split(",")
-#             max_x, max_y = image_coords[2].split(",")
-#             img_tmp_dir = "OCR-D-IMG/test_A"
-#             img_dir = os.path.dirname(str(fname))
-#             # Path of pix2pixHD
-#             Path(img_tmp_dir).mkdir(parents=True, exist_ok=True)
-
-#             crop_region = int(min_x), int(
-#                 min_y), int(max_x), int(max_y)
-#             cropped_img = self.crop_image(fname, crop_region)
-
-
-#             base, _ = ocrolib.allsplitext(fname)
-#             filename = base.split("/")[-1] + ".png"
-#             cropped_img.save(img_tmp_dir + "/" + filename)                    
-
-#             os.system("python " + str(path) + "/test.py --dataroot %s --checkpoints_dir ./ --name models --results_dir %s --label_nc 0 --no_instance --no_flip --resize_or_crop none --n_blocks_global 10 --n_local_enhancers 2 --gpu_ids %s --loadSize %d --fineSize %d --resize_or_crop %s" %
-#                       (os.path.dirname(img_tmp_dir), img_dir, self.parameter['gpu_id'], self.parameter['resizeHeight'], self.parameter['resizeWidth'], self.parameter['imgresize']))
-#             synthesized_image = filename.split(
-#                 ".")[0] + "_synthesized_image.jpg"
-#             pix2pix_img_dir = img_dir + "/models/test_latest/images/"
-#             dewarped_image = Path(pix2pix_img_dir + synthesized_image)
-#             if(dewarped_image.is_file()):
-#                 shutil.copy(dewarped_image, img_dir + "/" +
-#                             filename.split(".")[0] + ".dw.jpg")
-
-#             if(Path(img_tmp_dir).is_dir()):
-#                 shutil.rmtree(img_tmp_dir)
-#             if(Path(img_dir + "/models").is_dir()):
-#                 shutil.rmtree(img_dir + "/models")
-