quoccuongle/MultimodalOCR
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

IAM ReCTS

Browse Source
This commit is contained in:
echo840
2023-06-09 10:29:18 +08:00
parent 3c59897aa6
commit e22b12b169
185 changed files with 294244 additions and 22 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
datasets/process/process_ESTVQA.py Normal file → Executable file
View File

@@ -5,8 +5,8 @@ def has_chinese_characters(string):
pattern = re.compile(r'[\u4e00-\u9fa5]')
return bool(pattern.search(string))
if __name__ == "__main__":
ann_file = "/home/zhangli/GPT4/MutimodelOCR/data/ESTVQA/annotations/train.json"
img_file = "/home/zhangli/GPT4/MutimodelOCR/data/ESTVQA/images/train"
ann_file = "/home/zhangli/OCRData/data/TextVQA/ESTVQA/annotations/train.json"
#img_file = "/home/zhangli/GPT4/MutimodelOCR/data/ESTVQA/images/train"
cn_list = []
en_list= []
with open(ann_file,'r') as f: