qurator-spk/eynollah
1
0
Fork 0
mirror of https://github.com/qurator-spk/eynollah.git synced 2025-12-01 08:44:13 +01:00
Code Issues Projects Releases Wiki Activity

🔥 remove torch pinning

Browse source
This commit is contained in:
kba 2025-11-26 19:23:49 +01:00
parent e503c1a0b7
commit 000af16a47
2 changed files with 8 additions and 12 deletions
Download patch file Download diff file Expand all files Collapse all files

2
requirements-ocr.txt
View file

@ -1,2 +1,2 @@
torch <= 2.0.1 torch
transformers <= 4.30.2 transformers <= 4.30.2

18
src/eynollah/sbb_binarize.py
View file

@ -9,15 +9,13 @@ Tool to load model and binarize a given image.
import os import os
import logging import logging
from pathlib import Path from typing import Optional
from typing import Dict, Optional
import numpy as np import numpy as np
import cv2 import cv2
from ocrd_utils import tf_disable_interactive_logs from ocrd_utils import tf_disable_interactive_logs
from eynollah.model_zoo import EynollahModelZoo from eynollah.model_zoo import EynollahModelZoo
from eynollah.model_zoo.types import AnyModel
tf_disable_interactive_logs() tf_disable_interactive_logs()
import tensorflow as tf import tensorflow as tf
from tensorflow.python.keras import backend as tensorflow_backend from tensorflow.python.keras import backend as tensorflow_backend
@ -323,7 +321,7 @@ class SbbBinarizer:
image = cv2.imread(image_path) image = cv2.imread(image_path)
img_last = 0 img_last = 0
model_file, model = self.models model_file, model = self.models
self.logger.info('Predicting %s with model %s [%s/%s]', image_path if image_path else '[image]', model_file) self.logger.info('Predicting %s with model %s', image_path if image_path else '[image]', model_file)
res = self.predict(model, image, use_patches) res = self.predict(model, image, use_patches)
img_fin = np.zeros((res.shape[0], res.shape[1], 3)) img_fin = np.zeros((res.shape[0], res.shape[1], 3))
@ -338,7 +336,6 @@ class SbbBinarizer:
img_fin = (res[:, :] == 0) * 255 img_fin = (res[:, :] == 0) * 255
img_last = img_last + img_fin img_last = img_last + img_fin
kernel = np.ones((5, 5), np.uint8)
img_last[:, :][img_last[:, :] > 0] = 255 img_last[:, :][img_last[:, :] > 0] = 255
img_last = (img_last[:, :] == 0) * 255 img_last = (img_last[:, :] == 0) * 255
if output: if output:
@ -348,13 +345,13 @@ class SbbBinarizer:
else: else:
ls_imgs = list(filter(is_image_filename, os.listdir(dir_in))) ls_imgs = list(filter(is_image_filename, os.listdir(dir_in)))
self.logger.info("Found %d image files to binarize in %s", len(ls_imgs), dir_in) self.logger.info("Found %d image files to binarize in %s", len(ls_imgs), dir_in)
for i, image_name in enumerate(ls_imgs): for i, image_path in enumerate(ls_imgs):
image_stem = image_name.split('.')[0] self.logger.info('Binarizing [%3d/%d] %s', i + 1, len(ls_imgs), image_path)
self.logger.info('Binarizing [%3d/%d] %s', i + 1, len(ls_imgs), image_name) image_stem = image_path.split('.')[0]
image = cv2.imread(os.path.join(dir_in,image_name) ) image = cv2.imread(os.path.join(dir_in,image_path) )
img_last = 0 img_last = 0
model_file, model = self.models model_file, model = self.models
self.logger.info('Predicting %s with model %s [%s/%s]', image_path if image_path else '[image]', model_file) self.logger.info('Predicting %s with model %s', image_path if image_path else '[image]', model_file)
res = self.predict(model, image, use_patches) res = self.predict(model, image, use_patches)
img_fin = np.zeros((res.shape[0], res.shape[1], 3)) img_fin = np.zeros((res.shape[0], res.shape[1], 3))
@ -369,7 +366,6 @@ class SbbBinarizer:
img_fin = (res[:, :] == 0) * 255 img_fin = (res[:, :] == 0) * 255
img_last = img_last + img_fin img_last = img_last + img_fin
kernel = np.ones((5, 5), np.uint8)
img_last[:, :][img_last[:, :] > 0] = 255 img_last[:, :][img_last[:, :] > 0] = 255
img_last = (img_last[:, :] == 0) * 255 img_last = (img_last[:, :] == 0) * 255