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

update for multi-language

This commit is contained in:
tink2123 2020-12-08 19:07:39 +08:00
parent 8a5566c974
commit dd0f8c1d89
7 changed files with 15 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
configs/rec/multi_language/rec_en_number_lite_train.yml
View File

@ -15,7 +15,7 @@ Global:
use_visualdl: False
infer_img:
# for data or label process
character_dict_path: ppocr/utils/ic15_dict.txt
character_dict_path: ppocr/utils/dict/ic15_dict.txt
character_type: ch
max_text_length: 25
infer_mode: False

4
configs/rec/multi_language/rec_french_lite_train.yml
View File

@ -15,7 +15,7 @@ Global:
use_visualdl: False
infer_img:
# for data or label process
character_dict_path: ppocr/utils/french_dict.txt
character_dict_path: ppocr/utils/dict/french_dict.txt
character_type: french
max_text_length: 25
infer_mode: False
@ -85,7 +85,7 @@ Eval:
dataset:
name: SimpleDataSet
data_dir: ./train_data/
label_file_list: ["./train_data/eval_list.txt"]
label_file_list: ["./train_data/train_list.txt"]
transforms:
- DecodeImage: # load image
img_mode: BGR

2
configs/rec/multi_language/rec_german_lite_train.yml
View File

@ -15,7 +15,7 @@ Global:
use_visualdl: False
infer_img:
# for data or label process
character_dict_path: ppocr/utils/german_dict.txt
character_dict_path: ppocr/utils/dict/german_dict.txt
character_type: german
max_text_length: 25
infer_mode: False

2
configs/rec/multi_language/rec_japan_lite_train.yml
View File

@ -15,7 +15,7 @@ Global:
use_visualdl: False
infer_img:
# for data or label process
character_dict_path: ppocr/utils/japan_dict.txt
character_dict_path: ppocr/utils/dict/japan_dict.txt
character_type: japan
max_text_length: 25
infer_mode: False

2
configs/rec/multi_language/rec_korean_lite_train.yml
View File

@ -15,7 +15,7 @@ Global:
use_visualdl: False
infer_img:
# for data or label process
character_dict_path: ppocr/utils/korean_dict.txt
character_dict_path: ppocr/utils/dict/korean_dict.txt
character_type: korean
max_text_length: 25
infer_mode: False

6
ppocr/data/imaug/label_ops.py
View File

@ -79,7 +79,9 @@ class BaseRecLabelEncode(object):
character_dict_path=None,
character_type='ch',
use_space_char=False):
support_character_type = ['ch', 'en', 'en_sensitive']
support_character_type = [
'ch', 'en', 'en_sensitive', 'french', 'german', 'japan', 'french'
]
assert character_type in support_character_type, "Only {} are supported now but get {}".format(
support_character_type, self.character_str)
@ -87,7 +89,7 @@ class BaseRecLabelEncode(object):
if character_type == "en":
self.character_str = "0123456789abcdefghijklmnopqrstuvwxyz"
dict_character = list(self.character_str)
elif character_type == "ch":
elif character_type in ["ch", "french", "german", "japan", "french"]:
self.character_str = ""
assert character_dict_path is not None, "character_dict_path should not be None when character_type is ch"
with open(character_dict_path, "rb") as fin:

8
ppocr/postprocess/rec_postprocess.py
View File

@ -23,14 +23,16 @@ class BaseRecLabelDecode(object):
character_dict_path=None,
character_type='ch',
use_space_char=False):
support_character_type = ['ch', 'en', 'en_sensitive']
support_character_type = [
'ch', 'en', 'en_sensitive', 'french', 'german', 'japan', 'french'
]
assert character_type in support_character_type, "Only {} are supported now but get {}".format(
support_character_type, self.character_str)
if character_type == "en":
self.character_str = "0123456789abcdefghijklmnopqrstuvwxyz"
dict_character = list(self.character_str)
elif character_type == "ch":
elif character_type in ["ch", "french", "german", "japan", "french"]:
self.character_str = ""
assert character_dict_path is not None, "character_dict_path should not be None when character_type is ch"
with open(character_dict_path, "rb") as fin:
@ -150,4 +152,4 @@ class AttnLabelDecode(BaseRecLabelDecode):
else:
assert False, "unsupport type %s in get_beg_end_flag_idx" \
% beg_or_end
return idx
return idx