opensource/PaddleOCR
3
0
Fork 0
mirror of https://github.com/PaddlePaddle/PaddleOCR.git synced 2026-10-24 23:44:40 +08:00
Code Issues Packages Projects Releases Wiki Activity

add metric mode

Browse Source
This commit is contained in:
Jethong
2021-04-21 16:20:24 +08:00
parent e2b84da866
commit 2f978f638b
3 changed files with 25 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ppocr/data/imaug/label_ops.py
+22 -4
View File
@@ -199,15 +199,33 @@ class E2ELabelEncode_test(BaseRecLabelEncode):
character_type, use_space_char)
def __call__(self, data):
texts = data['texts']
import json
padnum = len(self.dict)
label = data['label']
label = json.loads(label)
nBox = len(label)
boxes, txts, txt_tags = [], [], []
for bno in range(0, nBox):
box = label[bno]['points']
txt = label[bno]['transcription']
boxes.append(box)
txts.append(txt)
if txt in ['*', '###']:
txt_tags.append(True)
else:
txt_tags.append(False)
boxes = np.array(boxes, dtype=np.float32)
txt_tags = np.array(txt_tags, dtype=np.bool)
data['polys'] = boxes
data['ignore_tags'] = txt_tags
temp_texts = []
for text in texts:
for text in txts:
text = text.lower()
text = self.encode(text)
if text is None:
return None
text = text + [36] * (self.max_text_len - len(text)
) # use 36 to pad
text = text + [padnum] * (self.max_text_len - len(text)
) # use 36 to pad
temp_texts.append(text)
data['texts'] = np.array(temp_texts)
return data