p60975123
/
mindspore
forked from mindspore-Ecosystem/mindspore
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

!15491 add general_char.txt 

From: @pandoublefeng
Reviewed-by: @oacjiewen,@c_34
Signed-off-by: @c_34
This commit is contained in:
mindspore-ci-bot 2021-04-22 15:32:52 +08:00 committed by Gitee
parent 8487ce0c09 fc56a0cdb8
commit 7da72d1c98
4 changed files with 9658 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9640
model_zoo/official/cv/crnn_seq2seq_ocr/general_chars.txt Normal file
View File

File diff suppressed because it is too large Load Diff

1
model_zoo/official/cv/crnn_seq2seq_ocr/scripts/run_eval_ascend.sh
View File

@ -55,6 +55,7 @@ then
fi
mkdir ./eval
cp ../*.py ./eval
cp ../*.txt ./eval
cp *.sh ./eval
cp -r ../src ./eval
cd ./eval || exit

1
model_zoo/official/cv/crnn_seq2seq_ocr/src/config.py
View File

@ -28,6 +28,7 @@ config = ed({
"val_annotation_file": "",
"data_json": "",
"go_shift": 1,
"characters_dictionary": {"pad_id": 0, "go_id": 1, "eos_id": 2, "unk_id": 3},
"labels_not_use": [u'%#<23>?%', u'%#背景#%', u'%#不识<E4B88D>?%', u'#%不识<EFBFBD>?#', u'%#模糊#%', u'%#模糊#%'],
"vocab_path": "./general_chars.txt",

26
model_zoo/official/cv/crnn_seq2seq_ocr/src/create_mindrecord_files.py
View File

@ -19,8 +19,8 @@ import numpy as np
from mindspore.mindrecord import FileWriter
from src.config import config
from src.utils import initialize_vocabulary
from config import config
from utils import initialize_vocabulary
def serialize_annotation(img_path, lex, vocab):
@ -82,7 +82,7 @@ def create_fsns_label(image_dir, anno_file_dirs):
def fsns_train_data_to_mindrecord(mindrecord_dir, prefix="data_ocr.mindrecord", file_num=8):
anno_file_dirs = [config.train_annotation_file]
anno_file_dirs = [config.annotation_file]
images, image_path_dict, image_anno_dict = create_fsns_label(image_dir=config.data_root,
anno_file_dirs=anno_file_dirs)
vocab, _ = initialize_vocabulary(config.vocab_path)
@ -104,8 +104,8 @@ def fsns_train_data_to_mindrecord(mindrecord_dir, prefix="data_ocr.mindrecord",
image_path = image_path_dict[img_id]
annotation = image_anno_dict[img_id]
label_max_len = config.max_text_len
text_max_len = config.max_text_len - 2
label_max_len = config.max_length
text_max_len = config.max_length - 2
if len(annotation) > text_max_len:
continue
@ -151,8 +151,8 @@ def fsns_train_data_to_mindrecord(mindrecord_dir, prefix="data_ocr.mindrecord",
def fsns_val_data_to_mindrecord(mindrecord_dir, prefix="data_ocr.mindrecord", file_num=8):
anno_file_dirs = [config.train_annotation_file]
images, image_path_dict, image_anno_dict = create_fsns_label(image_dir=config.data_root,
anno_file_dirs = [config.val_annotation_file]
images, image_path_dict, image_anno_dict = create_fsns_label(image_dir=config.val_data_root,
anno_file_dirs=anno_file_dirs)
vocab, _ = initialize_vocabulary(config.vocab_path)
@ -171,8 +171,8 @@ def fsns_val_data_to_mindrecord(mindrecord_dir, prefix="data_ocr.mindrecord", fi
image_path = image_path_dict[img_id]
annotation = image_anno_dict[img_id]
label_max_len = config.max_text_len
text_max_len = config.max_text_len - 2
label_max_len = config.max_length
text_max_len = config.max_length - 2
if len(annotation) > text_max_len:
continue
@ -226,7 +226,7 @@ def create_mindrecord(dataset="fsns", prefix="fsns.mindrecord", is_training=True
print("{} dataset is not defined!".format(dataset))
if not is_training:
mindrecord_dir = os.path.join(config.mindrecord_dir, "val")
mindrecord_dir = os.path.join(config.mindrecord_dir, "test")
mindrecord_files = [os.path.join(mindrecord_dir, prefix + "0")]
if not os.path.exists(mindrecord_files[0]):
@ -243,3 +243,9 @@ def create_mindrecord(dataset="fsns", prefix="fsns.mindrecord", is_training=True
print("{} dataset is not defined!".format(dataset))
return mindrecord_files
if __name__ == '__main__':
create_mindrecord(is_training=True)
create_mindrecord(is_training=False)
print("END")