diff --git a/MANIFEST.in b/MANIFEST.in
index 4c16c09d588d39906e1fa581c901cd9fcd7778c8..e16f157d6e9dd249d6c6a14ae54313759a6752c4 100644
--- a/MANIFEST.in
+++ b/MANIFEST.in
@@ -4,4 +4,5 @@ include README.md
recursive-include ppocr/utils *.txt utility.py logging.py
recursive-include ppocr/data/ *.py
recursive-include ppocr/postprocess *.py
-recursive-include tools/infer *.py
\ No newline at end of file
+recursive-include tools/infer *.py
+recursive-include ppocr/utils/e2e_utils/ *.py
\ No newline at end of file
diff --git a/configs/rec/multi_language/generate_multi_language_configs.py b/configs/rec/multi_language/generate_multi_language_configs.py
index 027a65c0c73e4b39ebb3b407271450d23281aa80..c3e33c0eba72f21cd4022a492b5635ed258c8b39 100644
--- a/configs/rec/multi_language/generate_multi_language_configs.py
+++ b/configs/rec/multi_language/generate_multi_language_configs.py
@@ -19,21 +19,56 @@ import logging
logging.basicConfig(level=logging.INFO)
support_list = {
- 'it':'italian', 'xi':'spanish', 'pu':'portuguese', 'ru':'russian', 'ar':'arabic',
- 'ta':'tamil', 'ug':'uyghur', 'fa':'persian', 'ur':'urdu', 'rs':'serbian latin',
- 'oc':'occitan', 'rsc':'serbian cyrillic', 'bg':'bulgarian', 'uk':'ukranian', 'be':'belarusian',
- 'te':'telugu', 'ka':'kannada', 'chinese_cht':'chinese tradition','hi':'hindi','mr':'marathi',
- 'ne':'nepali',
+ 'it': 'italian',
+ 'xi': 'spanish',
+ 'pu': 'portuguese',
+ 'ru': 'russian',
+ 'ar': 'arabic',
+ 'ta': 'tamil',
+ 'ug': 'uyghur',
+ 'fa': 'persian',
+ 'ur': 'urdu',
+ 'rs': 'serbian latin',
+ 'oc': 'occitan',
+ 'rsc': 'serbian cyrillic',
+ 'bg': 'bulgarian',
+ 'uk': 'ukranian',
+ 'be': 'belarusian',
+ 'te': 'telugu',
+ 'ka': 'kannada',
+ 'chinese_cht': 'chinese tradition',
+ 'hi': 'hindi',
+ 'mr': 'marathi',
+ 'ne': 'nepali',
}
-assert(
- os.path.isfile("./rec_multi_language_lite_train.yml")
- ),"Loss basic configuration file rec_multi_language_lite_train.yml.\
+
+latin_lang = [
+ 'af', 'az', 'bs', 'cs', 'cy', 'da', 'de', 'es', 'et', 'fr', 'ga', 'hr',
+ 'hu', 'id', 'is', 'it', 'ku', 'la', 'lt', 'lv', 'mi', 'ms', 'mt', 'nl',
+ 'no', 'oc', 'pi', 'pl', 'pt', 'ro', 'rs_latin', 'sk', 'sl', 'sq', 'sv',
+ 'sw', 'tl', 'tr', 'uz', 'vi', 'latin'
+]
+arabic_lang = ['ar', 'fa', 'ug', 'ur']
+cyrillic_lang = [
+ 'ru', 'rs_cyrillic', 'be', 'bg', 'uk', 'mn', 'abq', 'ady', 'kbd', 'ava',
+ 'dar', 'inh', 'che', 'lbe', 'lez', 'tab', 'cyrillic'
+]
+devanagari_lang = [
+ 'hi', 'mr', 'ne', 'bh', 'mai', 'ang', 'bho', 'mah', 'sck', 'new', 'gom',
+ 'sa', 'bgc', 'devanagari'
+]
+multi_lang = latin_lang + arabic_lang + cyrillic_lang + devanagari_lang
+
+assert (os.path.isfile("./rec_multi_language_lite_train.yml")
+ ), "Loss basic configuration file rec_multi_language_lite_train.yml.\
You can download it from \
https://github.com/PaddlePaddle/PaddleOCR/tree/dygraph/configs/rec/multi_language/"
-
-global_config = yaml.load(open("./rec_multi_language_lite_train.yml", 'rb'), Loader=yaml.Loader)
+
+global_config = yaml.load(
+ open("./rec_multi_language_lite_train.yml", 'rb'), Loader=yaml.Loader)
project_path = os.path.abspath(os.path.join(os.getcwd(), "../../../"))
+
class ArgsParser(ArgumentParser):
def __init__(self):
super(ArgsParser, self).__init__(
@@ -41,15 +76,30 @@ class ArgsParser(ArgumentParser):
self.add_argument(
"-o", "--opt", nargs='+', help="set configuration options")
self.add_argument(
- "-l", "--language", nargs='+', help="set language type, support {}".format(support_list))
+ "-l",
+ "--language",
+ nargs='+',
+ help="set language type, support {}".format(support_list))
self.add_argument(
- "--train",type=str,help="you can use this command to change the train dataset default path")
+ "--train",
+ type=str,
+ help="you can use this command to change the train dataset default path"
+ )
self.add_argument(
- "--val",type=str,help="you can use this command to change the eval dataset default path")
+ "--val",
+ type=str,
+ help="you can use this command to change the eval dataset default path"
+ )
self.add_argument(
- "--dict",type=str,help="you can use this command to change the dictionary default path")
+ "--dict",
+ type=str,
+ help="you can use this command to change the dictionary default path"
+ )
self.add_argument(
- "--data_dir",type=str,help="you can use this command to change the dataset default root path")
+ "--data_dir",
+ type=str,
+ help="you can use this command to change the dataset default root path"
+ )
def parse_args(self, argv=None):
args = super(ArgsParser, self).parse_args(argv)
@@ -68,21 +118,38 @@ class ArgsParser(ArgumentParser):
return config
def _set_language(self, type):
- assert(type),"please use -l or --language to choose language type"
+ print("type:", type)
+ lang = type[0]
+ assert (type), "please use -l or --language to choose language type"
assert(
- type[0] in support_list.keys()
+ lang in support_list.keys() or lang in multi_lang
),"the sub_keys(-l or --language) can only be one of support list: \n{},\nbut get: {}, " \
- "please check your running command".format(support_list, type)
- global_config['Global']['character_dict_path'] = 'ppocr/utils/dict/{}_dict.txt'.format(type[0])
- global_config['Global']['save_model_dir'] = './output/rec_{}_lite'.format(type[0])
- global_config['Train']['dataset']['label_file_list'] = ["train_data/{}_train.txt".format(type[0])]
- global_config['Eval']['dataset']['label_file_list'] = ["train_data/{}_val.txt".format(type[0])]
- global_config['Global']['character_type'] = type[0]
- assert(
- os.path.isfile(os.path.join(project_path,global_config['Global']['character_dict_path']))
- ),"Loss default dictionary file {}_dict.txt.You can download it from \
-https://github.com/PaddlePaddle/PaddleOCR/tree/dygraph/ppocr/utils/dict/".format(type[0])
- return type[0]
+ "please check your running command".format(multi_lang, type)
+ if lang in latin_lang:
+ lang = "latin"
+ elif lang in arabic_lang:
+ lang = "arabic"
+ elif lang in cyrillic_lang:
+ lang = "cyrillic"
+ elif lang in devanagari_lang:
+ lang = "devanagari"
+ global_config['Global'][
+ 'character_dict_path'] = 'ppocr/utils/dict/{}_dict.txt'.format(lang)
+ global_config['Global'][
+ 'save_model_dir'] = './output/rec_{}_lite'.format(lang)
+ global_config['Train']['dataset'][
+ 'label_file_list'] = ["train_data/{}_train.txt".format(lang)]
+ global_config['Eval']['dataset'][
+ 'label_file_list'] = ["train_data/{}_val.txt".format(lang)]
+ global_config['Global']['character_type'] = lang
+ assert (
+ os.path.isfile(
+ os.path.join(project_path, global_config['Global'][
+ 'character_dict_path']))
+ ), "Loss default dictionary file {}_dict.txt.You can download it from \
+https://github.com/PaddlePaddle/PaddleOCR/tree/dygraph/ppocr/utils/dict/".format(
+ lang)
+ return lang
def merge_config(config):
@@ -110,43 +177,51 @@ def merge_config(config):
cur[sub_key] = value
else:
cur = cur[sub_key]
-
+
+
def loss_file(path):
- assert(
- os.path.exists(path)
- ),"There is no such file:{},Please do not forget to put in the specified file".format(path)
+ assert (
+ os.path.exists(path)
+ ), "There is no such file:{},Please do not forget to put in the specified file".format(
+ path)
+
-
if __name__ == '__main__':
FLAGS = ArgsParser().parse_args()
merge_config(FLAGS.opt)
save_file_path = 'rec_{}_lite_train.yml'.format(FLAGS.language)
if os.path.isfile(save_file_path):
os.remove(save_file_path)
-
+
if FLAGS.train:
global_config['Train']['dataset']['label_file_list'] = [FLAGS.train]
- train_label_path = os.path.join(project_path,FLAGS.train)
+ train_label_path = os.path.join(project_path, FLAGS.train)
loss_file(train_label_path)
if FLAGS.val:
global_config['Eval']['dataset']['label_file_list'] = [FLAGS.val]
- eval_label_path = os.path.join(project_path,FLAGS.val)
+ eval_label_path = os.path.join(project_path, FLAGS.val)
loss_file(eval_label_path)
if FLAGS.dict:
global_config['Global']['character_dict_path'] = FLAGS.dict
- dict_path = os.path.join(project_path,FLAGS.dict)
+ dict_path = os.path.join(project_path, FLAGS.dict)
loss_file(dict_path)
if FLAGS.data_dir:
global_config['Eval']['dataset']['data_dir'] = FLAGS.data_dir
global_config['Train']['dataset']['data_dir'] = FLAGS.data_dir
- data_dir = os.path.join(project_path,FLAGS.data_dir)
+ data_dir = os.path.join(project_path, FLAGS.data_dir)
loss_file(data_dir)
-
+
with open(save_file_path, 'w') as f:
- yaml.dump(dict(global_config), f, default_flow_style=False, sort_keys=False)
+ yaml.dump(
+ dict(global_config), f, default_flow_style=False, sort_keys=False)
logging.info("Project path is :{}".format(project_path))
- logging.info("Train list path set to :{}".format(global_config['Train']['dataset']['label_file_list'][0]))
- logging.info("Eval list path set to :{}".format(global_config['Eval']['dataset']['label_file_list'][0]))
- logging.info("Dataset root path set to :{}".format(global_config['Eval']['dataset']['data_dir']))
- logging.info("Dict path set to :{}".format(global_config['Global']['character_dict_path']))
- logging.info("Config file set to :configs/rec/multi_language/{}".format(save_file_path))
+ logging.info("Train list path set to :{}".format(global_config['Train'][
+ 'dataset']['label_file_list'][0]))
+ logging.info("Eval list path set to :{}".format(global_config['Eval'][
+ 'dataset']['label_file_list'][0]))
+ logging.info("Dataset root path set to :{}".format(global_config['Eval'][
+ 'dataset']['data_dir']))
+ logging.info("Dict path set to :{}".format(global_config['Global'][
+ 'character_dict_path']))
+ logging.info("Config file set to :configs/rec/multi_language/{}".
+ format(save_file_path))
diff --git a/configs/rec/multi_language/rec_arabic_lite_train.yml b/configs/rec/multi_language/rec_arabic_lite_train.yml
new file mode 100644
index 0000000000000000000000000000000000000000..6dcfd1b69988b09c7dfc05cdbacce9756ea1f7cb
--- /dev/null
+++ b/configs/rec/multi_language/rec_arabic_lite_train.yml
@@ -0,0 +1,111 @@
+Global:
+ use_gpu: true
+ epoch_num: 500
+ log_smooth_window: 20
+ print_batch_step: 10
+ save_model_dir: ./output/rec_arabic_lite
+ save_epoch_step: 3
+ eval_batch_step:
+ - 0
+ - 2000
+ cal_metric_during_train: true
+ pretrained_model: null
+ checkpoints: null
+ save_inference_dir: null
+ use_visualdl: false
+ infer_img: null
+ character_dict_path: ppocr/utils/dict/arabic_dict.txt
+ character_type: arabic
+ max_text_length: 25
+ infer_mode: false
+ use_space_char: true
+Optimizer:
+ name: Adam
+ beta1: 0.9
+ beta2: 0.999
+ lr:
+ name: Cosine
+ learning_rate: 0.001
+ regularizer:
+ name: L2
+ factor: 1.0e-05
+Architecture:
+ model_type: rec
+ algorithm: CRNN
+ Transform: null
+ Backbone:
+ name: MobileNetV3
+ scale: 0.5
+ model_name: small
+ small_stride:
+ - 1
+ - 2
+ - 2
+ - 2
+ Neck:
+ name: SequenceEncoder
+ encoder_type: rnn
+ hidden_size: 48
+ Head:
+ name: CTCHead
+ fc_decay: 1.0e-05
+Loss:
+ name: CTCLoss
+PostProcess:
+ name: CTCLabelDecode
+Metric:
+ name: RecMetric
+ main_indicator: acc
+Train:
+ dataset:
+ name: SimpleDataSet
+ data_dir: train_data/
+ label_file_list:
+ - train_data/arabic_train.txt
+ transforms:
+ - DecodeImage:
+ img_mode: BGR
+ channel_first: false
+ - RecAug: null
+ - CTCLabelEncode: null
+ - RecResizeImg:
+ image_shape:
+ - 3
+ - 32
+ - 320
+ - KeepKeys:
+ keep_keys:
+ - image
+ - label
+ - length
+ loader:
+ shuffle: true
+ batch_size_per_card: 256
+ drop_last: true
+ num_workers: 8
+Eval:
+ dataset:
+ name: SimpleDataSet
+ data_dir: train_data/
+ label_file_list:
+ - train_data/arabic_val.txt
+ transforms:
+ - DecodeImage:
+ img_mode: BGR
+ channel_first: false
+ - CTCLabelEncode: null
+ - RecResizeImg:
+ image_shape:
+ - 3
+ - 32
+ - 320
+ - KeepKeys:
+ keep_keys:
+ - image
+ - label
+ - length
+ loader:
+ shuffle: false
+ drop_last: false
+ batch_size_per_card: 256
+ num_workers: 8
diff --git a/configs/rec/multi_language/rec_cyrillic_lite_train.yml b/configs/rec/multi_language/rec_cyrillic_lite_train.yml
new file mode 100644
index 0000000000000000000000000000000000000000..52527c1dfb9a306429bbab9241c623581d546e45
--- /dev/null
+++ b/configs/rec/multi_language/rec_cyrillic_lite_train.yml
@@ -0,0 +1,111 @@
+Global:
+ use_gpu: true
+ epoch_num: 500
+ log_smooth_window: 20
+ print_batch_step: 10
+ save_model_dir: ./output/rec_cyrillic_lite
+ save_epoch_step: 3
+ eval_batch_step:
+ - 0
+ - 2000
+ cal_metric_during_train: true
+ pretrained_model: null
+ checkpoints: null
+ save_inference_dir: null
+ use_visualdl: false
+ infer_img: null
+ character_dict_path: ppocr/utils/dict/cyrillic_dict.txt
+ character_type: cyrillic
+ max_text_length: 25
+ infer_mode: false
+ use_space_char: true
+Optimizer:
+ name: Adam
+ beta1: 0.9
+ beta2: 0.999
+ lr:
+ name: Cosine
+ learning_rate: 0.001
+ regularizer:
+ name: L2
+ factor: 1.0e-05
+Architecture:
+ model_type: rec
+ algorithm: CRNN
+ Transform: null
+ Backbone:
+ name: MobileNetV3
+ scale: 0.5
+ model_name: small
+ small_stride:
+ - 1
+ - 2
+ - 2
+ - 2
+ Neck:
+ name: SequenceEncoder
+ encoder_type: rnn
+ hidden_size: 48
+ Head:
+ name: CTCHead
+ fc_decay: 1.0e-05
+Loss:
+ name: CTCLoss
+PostProcess:
+ name: CTCLabelDecode
+Metric:
+ name: RecMetric
+ main_indicator: acc
+Train:
+ dataset:
+ name: SimpleDataSet
+ data_dir: train_data/
+ label_file_list:
+ - train_data/cyrillic_train.txt
+ transforms:
+ - DecodeImage:
+ img_mode: BGR
+ channel_first: false
+ - RecAug: null
+ - CTCLabelEncode: null
+ - RecResizeImg:
+ image_shape:
+ - 3
+ - 32
+ - 320
+ - KeepKeys:
+ keep_keys:
+ - image
+ - label
+ - length
+ loader:
+ shuffle: true
+ batch_size_per_card: 256
+ drop_last: true
+ num_workers: 8
+Eval:
+ dataset:
+ name: SimpleDataSet
+ data_dir: train_data/
+ label_file_list:
+ - train_data/cyrillic_val.txt
+ transforms:
+ - DecodeImage:
+ img_mode: BGR
+ channel_first: false
+ - CTCLabelEncode: null
+ - RecResizeImg:
+ image_shape:
+ - 3
+ - 32
+ - 320
+ - KeepKeys:
+ keep_keys:
+ - image
+ - label
+ - length
+ loader:
+ shuffle: false
+ drop_last: false
+ batch_size_per_card: 256
+ num_workers: 8
diff --git a/configs/rec/multi_language/rec_devanagari_lite_train.yml b/configs/rec/multi_language/rec_devanagari_lite_train.yml
new file mode 100644
index 0000000000000000000000000000000000000000..e1a7c829c3e6d3c3a57f1d501cdd80a560703ec7
--- /dev/null
+++ b/configs/rec/multi_language/rec_devanagari_lite_train.yml
@@ -0,0 +1,111 @@
+Global:
+ use_gpu: true
+ epoch_num: 500
+ log_smooth_window: 20
+ print_batch_step: 10
+ save_model_dir: ./output/rec_devanagari_lite
+ save_epoch_step: 3
+ eval_batch_step:
+ - 0
+ - 2000
+ cal_metric_during_train: true
+ pretrained_model: null
+ checkpoints: null
+ save_inference_dir: null
+ use_visualdl: false
+ infer_img: null
+ character_dict_path: ppocr/utils/dict/devanagari_dict.txt
+ character_type: devanagari
+ max_text_length: 25
+ infer_mode: false
+ use_space_char: true
+Optimizer:
+ name: Adam
+ beta1: 0.9
+ beta2: 0.999
+ lr:
+ name: Cosine
+ learning_rate: 0.001
+ regularizer:
+ name: L2
+ factor: 1.0e-05
+Architecture:
+ model_type: rec
+ algorithm: CRNN
+ Transform: null
+ Backbone:
+ name: MobileNetV3
+ scale: 0.5
+ model_name: small
+ small_stride:
+ - 1
+ - 2
+ - 2
+ - 2
+ Neck:
+ name: SequenceEncoder
+ encoder_type: rnn
+ hidden_size: 48
+ Head:
+ name: CTCHead
+ fc_decay: 1.0e-05
+Loss:
+ name: CTCLoss
+PostProcess:
+ name: CTCLabelDecode
+Metric:
+ name: RecMetric
+ main_indicator: acc
+Train:
+ dataset:
+ name: SimpleDataSet
+ data_dir: train_data/
+ label_file_list:
+ - train_data/devanagari_train.txt
+ transforms:
+ - DecodeImage:
+ img_mode: BGR
+ channel_first: false
+ - RecAug: null
+ - CTCLabelEncode: null
+ - RecResizeImg:
+ image_shape:
+ - 3
+ - 32
+ - 320
+ - KeepKeys:
+ keep_keys:
+ - image
+ - label
+ - length
+ loader:
+ shuffle: true
+ batch_size_per_card: 256
+ drop_last: true
+ num_workers: 8
+Eval:
+ dataset:
+ name: SimpleDataSet
+ data_dir: train_data/
+ label_file_list:
+ - train_data/devanagari_val.txt
+ transforms:
+ - DecodeImage:
+ img_mode: BGR
+ channel_first: false
+ - CTCLabelEncode: null
+ - RecResizeImg:
+ image_shape:
+ - 3
+ - 32
+ - 320
+ - KeepKeys:
+ keep_keys:
+ - image
+ - label
+ - length
+ loader:
+ shuffle: false
+ drop_last: false
+ batch_size_per_card: 256
+ num_workers: 8
diff --git a/configs/rec/multi_language/rec_en_number_lite_train.yml b/configs/rec/multi_language/rec_en_number_lite_train.yml
index 13eda8481cad8ca308cd0629214b52146c3ebf13..fff4dfcd905b406964bb07cf14017af22f40e91e 100644
--- a/configs/rec/multi_language/rec_en_number_lite_train.yml
+++ b/configs/rec/multi_language/rec_en_number_lite_train.yml
@@ -15,11 +15,11 @@ Global:
use_visualdl: False
infer_img:
# for data or label process
- character_dict_path: ppocr/utils/dict/en_dict.txt
+ character_dict_path: ppocr/utils/en_dict.txt
character_type: EN
max_text_length: 25
infer_mode: False
- use_space_char: False
+ use_space_char: True
Optimizer:
diff --git a/configs/rec/multi_language/rec_latin_lite_train.yml b/configs/rec/multi_language/rec_latin_lite_train.yml
new file mode 100644
index 0000000000000000000000000000000000000000..e71112b4b4f0afd3ceab9f10078bc5d518ee9e59
--- /dev/null
+++ b/configs/rec/multi_language/rec_latin_lite_train.yml
@@ -0,0 +1,111 @@
+Global:
+ use_gpu: true
+ epoch_num: 500
+ log_smooth_window: 20
+ print_batch_step: 10
+ save_model_dir: ./output/rec_latin_lite
+ save_epoch_step: 3
+ eval_batch_step:
+ - 0
+ - 2000
+ cal_metric_during_train: true
+ pretrained_model: null
+ checkpoints: null
+ save_inference_dir: null
+ use_visualdl: false
+ infer_img: null
+ character_dict_path: ppocr/utils/dict/latin_dict.txt
+ character_type: latin
+ max_text_length: 25
+ infer_mode: false
+ use_space_char: true
+Optimizer:
+ name: Adam
+ beta1: 0.9
+ beta2: 0.999
+ lr:
+ name: Cosine
+ learning_rate: 0.001
+ regularizer:
+ name: L2
+ factor: 1.0e-05
+Architecture:
+ model_type: rec
+ algorithm: CRNN
+ Transform: null
+ Backbone:
+ name: MobileNetV3
+ scale: 0.5
+ model_name: small
+ small_stride:
+ - 1
+ - 2
+ - 2
+ - 2
+ Neck:
+ name: SequenceEncoder
+ encoder_type: rnn
+ hidden_size: 48
+ Head:
+ name: CTCHead
+ fc_decay: 1.0e-05
+Loss:
+ name: CTCLoss
+PostProcess:
+ name: CTCLabelDecode
+Metric:
+ name: RecMetric
+ main_indicator: acc
+Train:
+ dataset:
+ name: SimpleDataSet
+ data_dir: train_data/
+ label_file_list:
+ - train_data/latin_train.txt
+ transforms:
+ - DecodeImage:
+ img_mode: BGR
+ channel_first: false
+ - RecAug: null
+ - CTCLabelEncode: null
+ - RecResizeImg:
+ image_shape:
+ - 3
+ - 32
+ - 320
+ - KeepKeys:
+ keep_keys:
+ - image
+ - label
+ - length
+ loader:
+ shuffle: true
+ batch_size_per_card: 256
+ drop_last: true
+ num_workers: 8
+Eval:
+ dataset:
+ name: SimpleDataSet
+ data_dir: train_data/
+ label_file_list:
+ - train_data/latin_val.txt
+ transforms:
+ - DecodeImage:
+ img_mode: BGR
+ channel_first: false
+ - CTCLabelEncode: null
+ - RecResizeImg:
+ image_shape:
+ - 3
+ - 32
+ - 320
+ - KeepKeys:
+ keep_keys:
+ - image
+ - label
+ - length
+ loader:
+ shuffle: false
+ drop_last: false
+ batch_size_per_card: 256
+ num_workers: 8
diff --git a/deploy/cpp_infer/CMakeLists.txt b/deploy/cpp_infer/CMakeLists.txt
index 120cf06a04c8f1769bdcd153a74cd6ff0665cf93..bdcfefee2eb4c3fdd12efd021fdbdcfce648fd39 100644
--- a/deploy/cpp_infer/CMakeLists.txt
+++ b/deploy/cpp_infer/CMakeLists.txt
@@ -40,6 +40,7 @@ endif()
if (WIN32)
include_directories("${PADDLE_LIB}/paddle/fluid/inference")
include_directories("${PADDLE_LIB}/paddle/include")
+ link_directories("${PADDLE_LIB}/paddle/lib")
link_directories("${PADDLE_LIB}/paddle/fluid/inference")
find_package(OpenCV REQUIRED PATHS ${OPENCV_DIR}/build/ NO_DEFAULT_PATH)
@@ -140,22 +141,22 @@ else()
endif ()
endif()
-# Note: libpaddle_inference_api.so/a must put before libpaddle_fluid.so/a
+# Note: libpaddle_inference_api.so/a must put before libpaddle_inference.so/a
if(WITH_STATIC_LIB)
if(WIN32)
set(DEPS
- ${PADDLE_LIB}/paddle/lib/paddle_fluid${CMAKE_STATIC_LIBRARY_SUFFIX})
+ ${PADDLE_LIB}/paddle/lib/paddle_inference${CMAKE_STATIC_LIBRARY_SUFFIX})
else()
set(DEPS
- ${PADDLE_LIB}/paddle/lib/libpaddle_fluid${CMAKE_STATIC_LIBRARY_SUFFIX})
+ ${PADDLE_LIB}/paddle/lib/libpaddle_inference${CMAKE_STATIC_LIBRARY_SUFFIX})
endif()
else()
if(WIN32)
set(DEPS
- ${PADDLE_LIB}/paddle/lib/paddle_fluid${CMAKE_SHARED_LIBRARY_SUFFIX})
+ ${PADDLE_LIB}/paddle/lib/paddle_inference${CMAKE_SHARED_LIBRARY_SUFFIX})
else()
set(DEPS
- ${PADDLE_LIB}/paddle/lib/libpaddle_fluid${CMAKE_SHARED_LIBRARY_SUFFIX})
+ ${PADDLE_LIB}/paddle/lib/libpaddle_inference${CMAKE_SHARED_LIBRARY_SUFFIX})
endif()
endif(WITH_STATIC_LIB)
diff --git a/deploy/cpp_infer/imgs/cpp_infer_pred_12.png b/deploy/cpp_infer/imgs/cpp_infer_pred_12.png
new file mode 100644
index 0000000000000000000000000000000000000000..eb5f64e1f6c329f7ae772c50edce7fc8afcb1211
Binary files /dev/null and b/deploy/cpp_infer/imgs/cpp_infer_pred_12.png differ
diff --git a/deploy/cpp_infer/readme.md b/deploy/cpp_infer/readme.md
index 633553082160ddc37944feadd35287ebcee9bdef..b62b1a4cf10b5abd345528ebf48e6a8de4387469 100644
--- a/deploy/cpp_infer/readme.md
+++ b/deploy/cpp_infer/readme.md
@@ -74,9 +74,10 @@ opencv3/
* 有2种方式获取Paddle预测库,下面进行详细介绍。
+
#### 1.2.1 直接下载安装
-* [Paddle预测库官网](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/guides/05_inference_deployment/inference/build_and_install_lib_cn.html)上提供了不同cuda版本的Linux预测库,可以在官网查看并选择合适的预测库版本。
+* [Paddle预测库官网](https://www.paddlepaddle.org.cn/documentation/docs/zh/advanced_guide/inference_deployment/inference/build_and_install_lib_cn.html)上提供了不同cuda版本的Linux预测库,可以在官网查看并选择合适的预测库版本(*建议选择paddle版本>=2.0.1版本的预测库* )。
* 下载之后使用下面的方法解压。
@@ -130,8 +131,6 @@ build/paddle_inference_install_dir/
其中`paddle`就是C++预测所需的Paddle库,`version.txt`中包含当前预测库的版本信息。
-
-
## 2 开始运行
### 2.1 将模型导出为inference model
@@ -232,7 +231,7 @@ visualize 1 # 是否对结果进行可视化,为1时,会在当前文件夹
最终屏幕上会输出检测结果如下。
-
![](../imgs/cpp_infer_pred_12.png)
+
diff --git a/deploy/cpp_infer/readme_en.md b/deploy/cpp_infer/readme_en.md
index cfe18a286fef022d83e61ea02465c0497f0f3d8c..cfda7ca05d49b9ba2534aa6bfc797425bb0dc6c5 100644
--- a/deploy/cpp_infer/readme_en.md
+++ b/deploy/cpp_infer/readme_en.md
@@ -91,8 +91,8 @@ tar -xf paddle_inference.tgz
Finally you can see the following files in the folder of `paddle_inference/`.
#### 1.2.2 Compile from the source code
-* If you want to get the latest Paddle inference library features, you can download the latest code from Paddle github repository and compile the inference library from the source code.
-* You can refer to [Paddle inference library] (https://www.paddlepaddle.org.cn/documentation/docs/en/develop/guides/05_inference_deployment/inference/build_and_install_lib_en.html) to get the Paddle source code from github, and then compile To generate the latest inference library. The method of using git to access the code is as follows.
+* If you want to get the latest Paddle inference library features, you can download the latest code from Paddle github repository and compile the inference library from the source code. It is recommended to download the inference library with paddle version greater than or equal to 2.0.1.
+* You can refer to [Paddle inference library] (https://www.paddlepaddle.org.cn/documentation/docs/en/advanced_guide/inference_deployment/inference/build_and_install_lib_en.html) to get the Paddle source code from github, and then compile To generate the latest inference library. The method of using git to access the code is as follows.
```shell
@@ -238,7 +238,7 @@ visualize 1 # Whether to visualize the results,when it is set as 1, The predic
The detection results will be shown on the screen, which is as follows.
-
![](../imgs/cpp_infer_pred_12.png)
+
diff --git a/doc/doc_ch/models_list.md b/doc/doc_ch/models_list.md
index d647d032674693466525d12c25b15c961e0eb86f..4842a8c57ba7893b5753cde04ae54399a45d8a56 100644
--- a/doc/doc_ch/models_list.md
+++ b/doc/doc_ch/models_list.md
@@ -104,27 +104,16 @@ python3 generate_multi_language_configs.py -l it \
| german_mobile_v2.0_rec |德文识别|[rec_german_lite_train.yml](../../configs/rec/multi_language/rec_german_lite_train.yml)|2.65M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/german_mobile_v2.0_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/german_mobile_v2.0_rec_train.tar) |
| korean_mobile_v2.0_rec |韩文识别|[rec_korean_lite_train.yml](../../configs/rec/multi_language/rec_korean_lite_train.yml)|3.9M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/korean_mobile_v2.0_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/korean_mobile_v2.0_rec_train.tar) |
| japan_mobile_v2.0_rec |日文识别|[rec_japan_lite_train.yml](../../configs/rec/multi_language/rec_japan_lite_train.yml)|4.23M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/japan_mobile_v2.0_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/japan_mobile_v2.0_rec_train.tar) |
-| it_mobile_v2.0_rec |意大利文识别|rec_it_lite_train.yml|2.53M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/it_mobile_v2.0_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/it_mobile_v2.0_rec_train.tar) |
-| xi_mobile_v2.0_rec |西班牙文识别|rec_xi_lite_train.yml|2.53M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/xi_mobile_v2.0_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/xi_mobile_v2.0_rec_train.tar) |
-| pu_mobile_v2.0_rec |葡萄牙文识别|rec_pu_lite_train.yml|2.63M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/pu_mobile_v2.0_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/pu_mobile_v2.0_rec_train.tar) |
-| ru_mobile_v2.0_rec |俄罗斯文识别|rec_ru_lite_train.yml|2.63M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/ru_mobile_v2.0_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/ru_mobile_v2.0_rec_train.tar) |
-| ar_mobile_v2.0_rec |阿拉伯文识别|rec_ar_lite_train.yml|2.53M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/ar_mobile_v2.0_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/ar_mobile_v2.0_rec_train.tar) |
-| hi_mobile_v2.0_rec |印地文识别|rec_hi_lite_train.yml|2.63M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/hi_mobile_v2.0_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/hi_mobile_v2.0_rec_train.tar) |
| chinese_cht_mobile_v2.0_rec |中文繁体识别|rec_chinese_cht_lite_train.yml|5.63M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/chinese_cht_mobile_v2.0_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/chinese_cht_mobile_v2.0_rec_train.tar) |
-| ug_mobile_v2.0_rec |维吾尔文识别|rec_ug_lite_train.yml|2.63M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/ug_mobile_v2.0_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/ug_mobile_v2.0_rec_train.tar) |
-| fa_mobile_v2.0_rec |波斯文识别|rec_fa_lite_train.yml|2.63M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/fa_mobile_v2.0_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/fa_mobile_v2.0_rec_train.tar) |
-| ur_mobile_v2.0_rec |乌尔都文识别|rec_ur_lite_train.yml|2.63M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/ur_mobile_v2.0_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/ur_mobile_v2.0_rec_train.tar) |
-| rs_mobile_v2.0_rec |塞尔维亚文(latin)识别|rec_rs_lite_train.yml|2.53M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/rs_mobile_v2.0_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/rs_mobile_v2.0_rec_train.tar) |
-| oc_mobile_v2.0_rec |欧西坦文识别|rec_oc_lite_train.yml|2.53M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/oc_mobile_v2.0_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/oc_mobile_v2.0_rec_train.tar) |
-| mr_mobile_v2.0_rec |马拉地文识别|rec_mr_lite_train.yml|2.63M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/mr_mobile_v2.0_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/mr_mobile_v2.0_rec_train.tar) |
-| ne_mobile_v2.0_rec |尼泊尔文识别|rec_ne_lite_train.yml|2.63M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/ne_mobile_v2.0_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/ne_mobile_v2.0_rec_train.tar) |
-| rsc_mobile_v2.0_rec |塞尔维亚文(cyrillic)识别|rec_rsc_lite_train.yml|2.63M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/rsc_mobile_v2.0_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/rsc_mobile_v2.0_rec_train.tar) |
-| bg_mobile_v2.0_rec |保加利亚文识别|rec_bg_lite_train.yml|2.63M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/bg_mobile_v2.0_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/bg_mobile_v2.0_rec_train.tar) |
-| uk_mobile_v2.0_rec |乌克兰文识别|rec_uk_lite_train.yml|2.63M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/uk_mobile_v2.0_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/uk_mobile_v2.0_rec_train.tar) |
-| be_mobile_v2.0_rec |白俄罗斯文识别|rec_be_lite_train.yml|2.63M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/be_mobile_v2.0_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/be_mobile_v2.0_rec_train.tar) |
| te_mobile_v2.0_rec |泰卢固文识别|rec_te_lite_train.yml|2.63M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/te_mobile_v2.0_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/te_mobile_v2.0_rec_train.tar) |
| ka_mobile_v2.0_rec |卡纳达文识别|rec_ka_lite_train.yml|2.63M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/ka_mobile_v2.0_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/ka_mobile_v2.0_rec_train.tar) |
| ta_mobile_v2.0_rec |泰米尔文识别|rec_ta_lite_train.yml|2.63M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/ta_mobile_v2.0_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/ta_mobile_v2.0_rec_train.tar) |
+| latin_mobile_v2.0_rec | 拉丁文识别 | [rec_latin_lite_train.yml](../../configs/rec/multi_language/rec_latin_lite_train.yml) |2.6M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/latin_ppocr_mobile_v2.0_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/latin_ppocr_mobile_v2.0_rec_train.tar) |
+| arabic_mobile_v2.0_rec | 阿拉伯字母 | [rec_arabic_lite_train.yml](../../configs/rec/multi_language/rec_arabic_lite_train.yml) |2.6M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/arabic_ppocr_mobile_v2.0_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/arabic_ppocr_mobile_v2.0_rec_train.tar) |
+| cyrillic_mobile_v2.0_rec | 斯拉夫字母 | [rec_cyrillic_lite_train.yml](../../configs/rec/multi_language/rec_cyrillic_lite_train.yml) |2.6M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/cyrillic_ppocr_mobile_v2.0_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/cyrillic_ppocr_mobile_v2.0_rec_train.tar) |
+| devanagari_mobile_v2.0_rec | 梵文字母 | [rec_devanagari_lite_train.yml](../../configs/rec/multi_language/rec_devanagari_lite_train.yml) |2.6M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/devanagari_ppocr_mobile_v2.0_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/devanagari_ppocr_mobile_v2.0_rec_train.tar) |
+
+更多支持语种请参考: [多语言模型](https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.1/doc/doc_ch/multi_languages.md#%E8%AF%AD%E7%A7%8D%E7%BC%A9%E5%86%99)
diff --git a/doc/doc_ch/multi_languages.md b/doc/doc_ch/multi_languages.md
index eec09535e7242f62cdebda97cee11086e45c1096..4e84c08582448722fa9e213ba64abfecd4f190eb 100644
--- a/doc/doc_ch/multi_languages.md
+++ b/doc/doc_ch/multi_languages.md
@@ -59,7 +59,7 @@ pip instll paddlepaddle-gpu
pip 安装
```
-pip install "paddleocr>=2.0.4" # 推荐使用2.0.4版本
+pip install "paddleocr>=2.0.6" # 推荐使用2.0.6版本
```
本地构建并安装
```
diff --git a/doc/doc_ch/recognition.md b/doc/doc_ch/recognition.md
index 907cf24e1a31104096ab6c0cf0819457852d1490..8a7c341cf24738b8af8c974a6da41bcb1b51ce48 100644
--- a/doc/doc_ch/recognition.md
+++ b/doc/doc_ch/recognition.md
@@ -138,7 +138,7 @@ PaddleOCR内置了一部分字典,可以按需使用。
`ppocr/utils/dict/german_dict.txt` 是一个包含131个字符的德文字典
-`ppocr/utils/dict/en_dict.txt` 是一个包含63个字符的英文字典
+`ppocr/utils/en_dict.txt` 是一个包含96个字符的英文字典
@@ -285,7 +285,7 @@ Eval:
#### 2.3 小语种
-PaddleOCR目前已支持26种(除中文外)语种识别,`configs/rec/multi_languages` 路径下提供了一个多语言的配置文件模版: [rec_multi_language_lite_train.yml](../../configs/rec/multi_language/rec_multi_language_lite_train.yml)。
+PaddleOCR目前已支持80种(除中文外)语种识别,`configs/rec/multi_languages` 路径下提供了一个多语言的配置文件模版: [rec_multi_language_lite_train.yml](../../configs/rec/multi_language/rec_multi_language_lite_train.yml)。
您有两种方式创建所需的配置文件:
@@ -368,26 +368,12 @@ PaddleOCR目前已支持26种(除中文外)语种识别,`configs/rec/multi
| rec_ger_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 德语 | german |
| rec_japan_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 日语 | japan |
| rec_korean_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 韩语 | korean |
-| rec_it_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 意大利语 | it |
-| rec_xi_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 西班牙语 | xi |
-| rec_pu_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 葡萄牙语 | pu |
-| rec_ru_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 俄罗斯语 | ru |
-| rec_ar_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 阿拉伯语 | ar |
-| rec_hi_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 印地语 | hi |
-| rec_ug_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 维吾尔语 | ug |
-| rec_fa_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 波斯语 | fa |
-| rec_ur_ite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 乌尔都语 | ur |
-| rec_rs_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 塞尔维亚(latin)语 | rs |
-| rec_oc_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 欧西坦语 | oc |
-| rec_mr_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 马拉地语 | mr |
-| rec_ne_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 尼泊尔语 | ne |
-| rec_rsc_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 塞尔维亚(cyrillic)语 | rsc |
-| rec_bg_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 保加利亚语 | bg |
-| rec_uk_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 乌克兰语 | uk |
-| rec_be_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 白俄罗斯语 | be |
-| rec_te_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 泰卢固语 | te |
-| rec_ka_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 卡纳达语 | ka |
-| rec_ta_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 泰米尔语 | ta |
+| rec_latin_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 拉丁字母 | latin |
+| rec_arabic_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 阿拉伯字母 | ar |
+| rec_cyrillic_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 斯拉夫字母 | cyrillic |
+| rec_devanagari_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 梵文字母 | devanagari |
+
+更多支持语种请参考: [多语言模型](https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.1/doc/doc_ch/multi_languages.md#%E8%AF%AD%E7%A7%8D%E7%BC%A9%E5%86%99)
多语言模型训练方式与中文模型一致,训练数据集均为100w的合成数据,少量的字体可以在 [百度网盘](https://pan.baidu.com/s/1bS_u207Rm7YbY33wOECKDA) 上下载,提取码:frgi。
diff --git a/doc/doc_en/models_list_en.md b/doc/doc_en/models_list_en.md
index e0163972b94ddfde8215cd323e2ba037752d3b4c..7d5b0d086fc7e8b329e4fba475bb36445d05d018 100644
--- a/doc/doc_en/models_list_en.md
+++ b/doc/doc_en/models_list_en.md
@@ -102,27 +102,16 @@ python3 generate_multi_language_configs.py -l it \
| german_mobile_v2.0_rec |Lightweight model for German recognition|[rec_german_lite_train.yml](../../configs/rec/multi_language/rec_german_lite_train.yml)|2.65M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/german_mobile_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/german_mobile_v2.0_rec_train.tar) |
| korean_mobile_v2.0_rec |Lightweight model for Korean recognition|[rec_korean_lite_train.yml](../../configs/rec/multi_language/rec_korean_lite_train.yml)|3.9M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/korean_mobile_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/korean_mobile_v2.0_rec_train.tar) |
| japan_mobile_v2.0_rec |Lightweight model for Japanese recognition|[rec_japan_lite_train.yml](../../configs/rec/multi_language/rec_japan_lite_train.yml)|4.23M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/japan_mobile_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/japan_mobile_v2.0_rec_train.tar) |
-| it_mobile_v2.0_rec |Lightweight model for Italian recognition|rec_it_lite_train.yml|2.53M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/it_mobile_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/it_mobile_v2.0_rec_train.tar) |
-| xi_mobile_v2.0_rec |Lightweight model for Spanish recognition|rec_xi_lite_train.yml|2.53M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/xi_mobile_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/xi_mobile_v2.0_rec_train.tar) |
-| pu_mobile_v2.0_rec |Lightweight model for Portuguese recognition|rec_pu_lite_train.yml|2.63M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/pu_mobile_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/pu_mobile_v2.0_rec_train.tar) |
-| ru_mobile_v2.0_rec |Lightweight model for Russia recognition|rec_ru_lite_train.yml|2.63M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/ru_mobile_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/ru_mobile_v2.0_rec_train.tar) |
-| ar_mobile_v2.0_rec |Lightweight model for Arabic recognition|rec_ar_lite_train.yml|2.53M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/ar_mobile_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/ar_mobile_v2.0_rec_train.tar) |
-| hi_mobile_v2.0_rec |Lightweight model for Hindi recognition|rec_hi_lite_train.yml|2.63M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/hi_mobile_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/hi_mobile_v2.0_rec_train.tar) |
-| chinese_cht_mobile_v2.0_rec |Lightweight model for chinese traditional recognition|rec_chinese_cht_lite_train.yml|5.63M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/chinese_cht_mobile_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/chinese_cht_mobile_v2.0_rec_train.tar) |
-| ug_mobile_v2.0_rec |Lightweight model for Uyghur recognition|rec_ug_lite_train.yml|2.63M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/ug_mobile_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/ug_mobile_v2.0_rec_train.tar) |
-| fa_mobile_v2.0_rec |Lightweight model for Persian recognition|rec_fa_lite_train.yml|2.63M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/fa_mobile_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/fa_mobile_v2.0_rec_train.tar) |
-| ur_mobile_v2.0_rec |Lightweight model for Urdu recognition|rec_ur_lite_train.yml|2.63M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/ur_mobile_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/ur_mobile_v2.0_rec_train.tar) |
-| rs_mobile_v2.0_rec |Lightweight model for Serbian(latin) recognition|rec_rs_lite_train.yml|2.53M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/rs_mobile_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/rs_mobile_v2.0_rec_train.tar) |
-| oc_mobile_v2.0_rec |Lightweight model for Occitan recognition|rec_oc_lite_train.yml|2.53M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/oc_mobile_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/oc_mobile_v2.0_rec_train.tar) |
-| mr_mobile_v2.0_rec |Lightweight model for Marathi recognition|rec_mr_lite_train.yml|2.63M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/mr_mobile_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/mr_mobile_v2.0_rec_train.tar) |
-| ne_mobile_v2.0_rec |Lightweight model for Nepali recognition|rec_ne_lite_train.yml|2.63M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/ne_mobile_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/ne_mobile_v2.0_rec_train.tar) |
-| rsc_mobile_v2.0_rec |Lightweight model for Serbian(cyrillic) recognition|rec_rsc_lite_train.yml|2.63M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/rsc_mobile_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/rsc_mobile_v2.0_rec_train.tar) |
-| bg_mobile_v2.0_rec |Lightweight model for Bulgarian recognition|rec_bg_lite_train.yml|2.63M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/bg_mobile_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/bg_mobile_v2.0_rec_train.tar) |
-| uk_mobile_v2.0_rec |Lightweight model for Ukranian recognition|rec_uk_lite_train.yml|2.63M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/uk_mobile_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/uk_mobile_v2.0_rec_train.tar) |
-| be_mobile_v2.0_rec |Lightweight model for Belarusian recognition|rec_be_lite_train.yml|2.63M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/be_mobile_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/be_mobile_v2.0_rec_train.tar) |
+| chinese_cht_mobile_v2.0_rec |Lightweight model for chinese cht recognition|rec_chinese_cht_lite_train.yml|5.63M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/chinese_cht_mobile_v2.0_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/chinese_cht_mobile_v2.0_rec_train.tar) |
| te_mobile_v2.0_rec |Lightweight model for Telugu recognition|rec_te_lite_train.yml|2.63M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/te_mobile_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/te_mobile_v2.0_rec_train.tar) |
| ka_mobile_v2.0_rec |Lightweight model for Kannada recognition|rec_ka_lite_train.yml|2.63M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/ka_mobile_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/ka_mobile_v2.0_rec_train.tar) |
| ta_mobile_v2.0_rec |Lightweight model for Tamil recognition|rec_ta_lite_train.yml|2.63M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/ta_mobile_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/ta_mobile_v2.0_rec_train.tar) |
+| latin_mobile_v2.0_rec | Lightweight model for latin recognition | [rec_latin_lite_train.yml](../../configs/rec/multi_language/rec_latin_lite_train.yml) |2.6M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/latin_ppocr_mobile_v2.0_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/latin_ppocr_mobile_v2.0_rec_train.tar) |
+| arabic_mobile_v2.0_rec | Lightweight model for arabic recognition | [rec_arabic_lite_train.yml](../../configs/rec/multi_language/rec_arabic_lite_train.yml) |2.6M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/arabic_ppocr_mobile_v2.0_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/arabic_ppocr_mobile_v2.0_rec_train.tar) |
+| cyrillic_mobile_v2.0_rec | Lightweight model for cyrillic recognition | [rec_cyrillic_lite_train.yml](../../configs/rec/multi_language/rec_cyrillic_lite_train.yml) |2.6M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/cyrillic_ppocr_mobile_v2.0_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/cyrillic_ppocr_mobile_v2.0_rec_train.tar) |
+| devanagari_mobile_v2.0_rec | Lightweight model for devanagari recognition | [rec_devanagari_lite_train.yml](../../configs/rec/multi_language/rec_devanagari_lite_train.yml) |2.6M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/devanagari_ppocr_mobile_v2.0_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/devanagari_ppocr_mobile_v2.0_rec_train.tar) |
+
+For more supported languages, please refer to : [Multi-language model](https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.1/doc/doc_en/multi_languages_en.md#4-support-languages-and-abbreviations)
diff --git a/doc/doc_en/multi_languages_en.md b/doc/doc_en/multi_languages_en.md
index 3f4f02266f4708efb7fdd3e9211678af7028c9df..3a7dde9600fd4081b413c2c01747a8c1f610e5f6 100644
--- a/doc/doc_en/multi_languages_en.md
+++ b/doc/doc_en/multi_languages_en.md
@@ -60,7 +60,7 @@ pip instll paddlepaddle-gpu
pip install
```
-pip install "paddleocr>=2.0.4" # 2.0.4 version is recommended
+pip install "paddleocr>=2.0.6" # 2.0.6 version is recommended
```
Build and install locally
```
diff --git a/doc/doc_en/recognition_en.md b/doc/doc_en/recognition_en.md
index aeb9aa0d43e400c4d6e733b2c9f4a74559dccecb..0b3db6a235bdbfeb930d6cf3f7d086829fd32c43 100644
--- a/doc/doc_en/recognition_en.md
+++ b/doc/doc_en/recognition_en.md
@@ -131,7 +131,7 @@ PaddleOCR has built-in dictionaries, which can be used on demand.
`ppocr/utils/dict/german_dict.txt` is a German dictionary with 131 characters
-`ppocr/utils/dict/en_dict.txt` is a English dictionary with 63 characters
+`ppocr/utils/en_dict.txt` is a English dictionary with 96 characters
The current multi-language model is still in the demo stage and will continue to optimize the model and add languages. **You are very welcome to provide us with dictionaries and fonts in other languages**,
@@ -279,7 +279,7 @@ Eval:
#### 2.3 Multi-language
-PaddleOCR currently supports 26 (except Chinese) language recognition. A multi-language configuration file template is
+PaddleOCR currently supports 80 (except Chinese) language recognition. A multi-language configuration file template is
provided under the path `configs/rec/multi_languages`: [rec_multi_language_lite_train.yml](../../configs/rec/multi_language/rec_multi_language_lite_train.yml)。
There are two ways to create the required configuration file::
@@ -368,27 +368,12 @@ Currently, the multi-language algorithms supported by PaddleOCR are:
| rec_ger_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | German | german |
| rec_japan_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | Japanese | japan |
| rec_korean_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | Korean | korean |
-| rec_it_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | Italian | it |
-| rec_xi_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | Spanish | xi |
-| rec_pu_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | Portuguese | pu |
-| rec_ru_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | Russia | ru |
-| rec_ar_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | Arabic | ar |
-| rec_hi_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | Hindi | hi |
-| rec_ug_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | Uyghur | ug |
-| rec_fa_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | Persian(Farsi) | fa |
-| rec_ur_ite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | Urdu | ur |
-| rec_rs_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | Serbian(latin) | rs |
-| rec_oc_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | Occitan | oc |
-| rec_mr_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | Marathi | mr |
-| rec_ne_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | Nepali | ne |
-| rec_rsc_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | Serbian(cyrillic) | rsc |
-| rec_bg_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | Bulgarian | bg |
-| rec_uk_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | Ukranian | uk |
-| rec_be_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | Belarusian | be |
-| rec_te_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | Telugu | te |
-| rec_ka_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | Kannada | ka |
-| rec_ta_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | Tamil | ta |
+| rec_latin_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | Latin | latin |
+| rec_arabic_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | arabic | ar |
+| rec_cyrillic_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | cyrillic | cyrillic |
+| rec_devanagari_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | devanagari | devanagari |
+For more supported languages, please refer to : [Multi-language model](https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.1/doc/doc_en/multi_languages_en.md#4-support-languages-and-abbreviations)
The multi-language model training method is the same as the Chinese model. The training data set is 100w synthetic data. A small amount of fonts and test data can be downloaded on [Baidu Netdisk](https://pan.baidu.com/s/1bS_u207Rm7YbY33wOECKDA),Extraction code:frgi.
diff --git a/paddleocr.py b/paddleocr.py
index 47e1267ac40effbe8b4ab80723c66eb5378be179..d5b6a01ba1fa8b233652de9b972f88643e89c5d8 100644
--- a/paddleocr.py
+++ b/paddleocr.py
@@ -34,8 +34,12 @@ from ppocr.utils.utility import check_and_read_gif, get_image_file_list
__all__ = ['PaddleOCR']
model_urls = {
- 'det':
- 'https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_infer.tar',
+ 'det': {
+ 'ch':
+ 'https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_infer.tar',
+ 'en':
+ 'https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/en_ppocr_mobile_v2.0_det_infer.tar'
+ },
'rec': {
'ch': {
'url':
@@ -45,7 +49,7 @@ model_urls = {
'en': {
'url':
'https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/en_number_mobile_v2.0_rec_infer.tar',
- 'dict_path': './ppocr/utils/dict/en_dict.txt'
+ 'dict_path': './ppocr/utils/en_dict.txt'
},
'french': {
'url':
@@ -113,7 +117,7 @@ model_urls = {
}
SUPPORT_DET_MODEL = ['DB']
-VERSION = 2.0
+VERSION = 2.1
SUPPORT_REC_MODEL = ['CRNN']
BASE_DIR = os.path.expanduser("~/.paddleocr/")
@@ -199,7 +203,7 @@ def parse_args(mMain=True, add_help=True):
parser.add_argument("--rec_model_dir", type=str, default=None)
parser.add_argument("--rec_image_shape", type=str, default="3, 32, 320")
parser.add_argument("--rec_char_type", type=str, default='ch')
- parser.add_argument("--rec_batch_num", type=int, default=30)
+ parser.add_argument("--rec_batch_num", type=int, default=6)
parser.add_argument("--max_text_length", type=int, default=25)
parser.add_argument("--rec_char_dict_path", type=str, default=None)
parser.add_argument("--use_space_char", type=bool, default=True)
@@ -209,7 +213,7 @@ def parse_args(mMain=True, add_help=True):
parser.add_argument("--cls_model_dir", type=str, default=None)
parser.add_argument("--cls_image_shape", type=str, default="3, 48, 192")
parser.add_argument("--label_list", type=list, default=['0', '180'])
- parser.add_argument("--cls_batch_num", type=int, default=30)
+ parser.add_argument("--cls_batch_num", type=int, default=6)
parser.add_argument("--cls_thresh", type=float, default=0.9)
parser.add_argument("--enable_mkldnn", type=bool, default=False)
@@ -243,7 +247,7 @@ def parse_args(mMain=True, add_help=True):
rec_model_dir=None,
rec_image_shape="3, 32, 320",
rec_char_type='ch',
- rec_batch_num=30,
+ rec_batch_num=6,
max_text_length=25,
rec_char_dict_path=None,
use_space_char=True,
@@ -251,7 +255,7 @@ def parse_args(mMain=True, add_help=True):
cls_model_dir=None,
cls_image_shape="3, 48, 192",
label_list=['0', '180'],
- cls_batch_num=30,
+ cls_batch_num=6,
cls_thresh=0.9,
enable_mkldnn=False,
use_zero_copy_run=False,
@@ -274,10 +278,10 @@ class PaddleOCR(predict_system.TextSystem):
self.use_angle_cls = postprocess_params.use_angle_cls
lang = postprocess_params.lang
latin_lang = [
- 'af', 'az', 'bs', 'cs', 'cy', 'da', 'de', 'en', 'es', 'et', 'fr',
- 'ga', 'hr', 'hu', 'id', 'is', 'it', 'ku', 'la', 'lt', 'lv', 'mi',
- 'ms', 'mt', 'nl', 'no', 'oc', 'pi', 'pl', 'pt', 'ro', 'rs_latin',
- 'sk', 'sl', 'sq', 'sv', 'sw', 'tl', 'tr', 'uz', 'vi'
+ 'af', 'az', 'bs', 'cs', 'cy', 'da', 'de', 'es', 'et', 'fr', 'ga',
+ 'hr', 'hu', 'id', 'is', 'it', 'ku', 'la', 'lt', 'lv', 'mi', 'ms',
+ 'mt', 'nl', 'no', 'oc', 'pi', 'pl', 'pt', 'ro', 'rs_latin', 'sk',
+ 'sl', 'sq', 'sv', 'sw', 'tl', 'tr', 'uz', 'vi'
]
arabic_lang = ['ar', 'fa', 'ug', 'ur']
cyrillic_lang = [
@@ -299,6 +303,10 @@ class PaddleOCR(predict_system.TextSystem):
assert lang in model_urls[
'rec'], 'param lang must in {}, but got {}'.format(
model_urls['rec'].keys(), lang)
+ if lang == "ch":
+ det_lang = "ch"
+ else:
+ det_lang = "en"
use_inner_dict = False
if postprocess_params.rec_char_dict_path is None:
use_inner_dict = True
@@ -308,7 +316,7 @@ class PaddleOCR(predict_system.TextSystem):
# init model dir
if postprocess_params.det_model_dir is None:
postprocess_params.det_model_dir = os.path.join(
- BASE_DIR, '{}/det'.format(VERSION))
+ BASE_DIR, '{}/det/{}'.format(VERSION, det_lang))
if postprocess_params.rec_model_dir is None:
postprocess_params.rec_model_dir = os.path.join(
BASE_DIR, '{}/rec/{}'.format(VERSION, lang))
@@ -317,7 +325,8 @@ class PaddleOCR(predict_system.TextSystem):
BASE_DIR, '{}/cls'.format(VERSION))
print(postprocess_params)
# download model
- maybe_download(postprocess_params.det_model_dir, model_urls['det'])
+ maybe_download(postprocess_params.det_model_dir,
+ model_urls['det'][det_lang])
maybe_download(postprocess_params.rec_model_dir,
model_urls['rec'][lang]['url'])
maybe_download(postprocess_params.cls_model_dir, model_urls['cls'])
diff --git a/setup.py b/setup.py
index d491adb17e6251355c0190d0ddecb9a82b09bc2e..a1ddbbb6d6d0c2657bb699a72bde75ef07ab3a94 100644
--- a/setup.py
+++ b/setup.py
@@ -32,7 +32,7 @@ setup(
package_dir={'paddleocr': ''},
include_package_data=True,
entry_points={"console_scripts": ["paddleocr= paddleocr.paddleocr:main"]},
- version='2.0.4',
+ version='2.0.6',
install_requires=requirements,
license='Apache License 2.0',
description='Awesome OCR toolkits based on PaddlePaddle (8.6M ultra-lightweight pre-trained model, support training and deployment among server, mobile, embeded and IoT devices',