jasder
/
PaddleOCR
mirror of https://mirror.trustie.net/root/PaddleOCR.git
1
0
Fork 1
Code Issues Releases Wiki Activity

Merge pull request #6254 from LDOUBLEV/dygraph 

[doc] add r50 base
This commit is contained in:
Evezerest 2022-05-12 16:32:30 +08:00 committed by GitHub
parent 59bafb8d4d e94d674623
commit a458c5a6ce
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
3 changed files with 8 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
doc/doc_ch/PP-OCRv3_introduction.md
View File

@ -53,11 +53,10 @@ PP-OCRv3检测模型是对PP-OCRv2中的[CML](https://arxiv.org/pdf/2109.03144.p
|序号|策略|模型大小|hmean|速度（cpu + mkldnn)|
|-|-|-|-|-|
|baseline teacher|PP-OCR server|49M|83.2%|171ms|
|baseline teacher|DB-R50|99M|83.5%|260ms|
|teacher1|DB-R50-LK-PAN|124M|85.0%|396ms|
|teacher2|DB-R50-LK-PAN-DML|124M|86.0%|396ms|
|baseline student|PP-OCRv2|3M|83.2%|117ms|
|student0|DB-MV3-RSE-FPN|3.6M|84.5%|124ms|
|student1|DB-MV3-CML（teacher2）|3M|84.3%|117ms|
|student2|DB-MV3-RSE-FPN-CML（teacher2）|3.6M|85.4%|124ms|

3
doc/doc_en/PP-OCRv3_introduction_en.md
View File

@ -55,11 +55,10 @@ The ablation experiments are as follows:
|ID|Strategy|Model Size|Hmean|The Inference Time（cpu + mkldnn)|
|-|-|-|-|-|
|baseline teacher|PP-OCR server|49M|83.2%|171ms|
|baseline teacher|DB-R50|99M|83.5%|260ms|
|teacher1|DB-R50-LK-PAN|124M|85.0%|396ms|
|teacher2|DB-R50-LK-PAN-DML|124M|86.0%|396ms|
|baseline student|PP-OCRv2|3M|83.2%|117ms|
|student0|DB-MV3-RSE-FPN|3.6M|84.5%|124ms|
|student1|DB-MV3-CML（teacher2）|3M|84.3%|117ms|
|student2|DB-MV3-RSE-FPN-CML（teacher2）|3.6M|85.4%|124ms|

7
ppocr/data/imaug/label_ops.py
View File

@ -438,7 +438,12 @@ class KieLabelEncode(object):
texts.append(ann['transcription'])
text_ind = [self.dict[c] for c in text if c in self.dict]
text_inds.append(text_ind)
labels.append(ann['label'])
if 'label' in anno.keys():
labels.append(ann['label'])
elif 'key_cls' in anno.keys():
labels.append(anno['key_cls'])
else:
raise ValueError("Cannot found 'key_cls' in ann.keys(), please check your training annotation.")
edges.append(ann.get('edge', 0))
ann_infos = dict(
image=data['image'],