forgetest5
/
PaddleOCR
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Merge pull request #94 from tink2123/win 

Adaptive Windows
This commit is contained in:
xiaoting 2020-05-25 18:49:15 +08:00 committed by GitHub
parent 6081c67b96 53952a46c6
commit c63624b3fd
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
4 changed files with 16 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
ppocr/data/det/dataset_traversal.py Executable file → Normal file
View File

@ -13,6 +13,7 @@
#limitations under the License.
import os
import sys
import math
import random
import functools
@ -42,6 +43,10 @@ class TrainReader(object):
img_num = len(label_infor_list)
img_id_list = list(range(img_num))
random.shuffle(img_id_list)
if sys.platform == "win32":
print("multiprocess is not fully compatible with Windows."
"num_workers will be 1.")
self.num_workers = 1
for img_id in range(process_id, img_num, self.num_workers):
label_infor = label_infor_list[img_id_list[img_id]]
outs = self.process(label_infor)

2
ppocr/data/reader_main.py
View File

@ -66,6 +66,8 @@ def reader_main(config=None, mode=None):
reader_function = params['reader_function']
function = create_module(reader_function)(params)
if mode == "train":
if sys.platform == "win32":
return function(0)
readers = []
num_workers = params['num_workers']
for process_id in range(num_workers):

10
ppocr/data/rec/dataset_traversal.py
View File

@ -13,6 +13,7 @@
#limitations under the License.
import os
import sys
import math
import random
import numpy as np
@ -191,16 +192,21 @@ class SimpleReader(object):
img_num = len(label_infor_list)
img_id_list = list(range(img_num))
random.shuffle(img_id_list)
if sys.platform=="win32":
print("multiprocess is not fully compatible with Windows."
"num_workers will be 1.")
self.num_workers = 1
for img_id in range(process_id, img_num, self.num_workers):
label_infor = label_infor_list[img_id_list[img_id]]
substr = label_infor.decode('utf-8').strip("\n").split("\t")
img_path = self.img_set_dir + "/" + substr[0]
img = cv2.imread(img_path)
if img.shape[-1]==1 or len(list(img.shape))==2:
img = cv2.cvtColor(img, cv2.COLOR_GRAY2BGR)
if img is None:
logger.info("{} does not exist!".format(img_path))
continue
if img.shape[-1]==1 or len(list(img.shape))==2:
img = cv2.cvtColor(img, cv2.COLOR_GRAY2BGR)
label = substr[1]
outs = process_image(img, self.image_shape, label,
self.char_ops, self.loss_type,

2
ppocr/utils/character.py
View File

@ -34,7 +34,7 @@ class CharacterOps(object):
with open(character_dict_path, "rb") as fin:
lines = fin.readlines()
for line in lines:
line = line.decode('utf-8').strip("\n")
line = line.decode('utf-8').strip("\n").strip("\r\n")
self.character_str += line
dict_character = list(self.character_str)
elif self.character_type == "en_sensitive":