Comments (4)
由于基于Attention损失的识别模型和基于CTC的识别模型推理差别很大,目前还在调试中。对于中文文本识别,建议优先选择基于CTC损失的识别模型,实践中也发现基于Attention损失的效果不如基于CTC损失的识别模型。
from paddleocr.
已解决attention模型转inference model的问题
from paddleocr.
@LDOUBLEV 你好,请问您是怎么解决的?我用export_model.py 转换attention模型为inference model的时候会报
ValueError: All elements in
shape
must be positive when it's a list or tuple
的错误。我的转换命令如下:
python3 tools/export_model.py -c configs/rec/rec_r34_vd_tps_bilstm_att.yml -o Global.checkpoints=./output/rec/rec_r34_vd_tps_bilstm_att/best_accuracy Global.save_inference_dir=./inference/rec_att
from paddleocr.
crnn配置中的attention 和ctc loss哪个准确率高?rec_r34_vd_none_bilstm_ctc.yml rec_r34_vd_none_none_ctc.yml rec_r34_vd_tps_bilstm_att.yml rec_r34_vd_tps_bilstm_ctc.yml
from paddleocr.
Related Issues (20)
- 在config里添加stop_gradient HOT 3
- ppocrv4 检测模型转tensorrt性能下降严重(着急) HOT 5
- ModuleNotFoundError: No module named 'paddle' HOT 2
- 手写数学公式识别算法-CAN-使用样例代码也无法识别 HOT 9
- paddleocr模型训练 HOT 2
- 字符间距大跟空格很像,造成空白区域被误识别成错误字符,如何解决? HOT 1
- pdf中原文放到txt中会比普通字符矮一些的非正常字符是什么字符?怎么转换成正常字符? HOT 2
- hubserving部署structure_table效果比通用表格识别差不少 HOT 1
- PP-OCRv4在线体验版使用离线推理的效果不一致 HOT 4
- 使用GPU时检测不到文字但CPU可以 HOT 9
- paddle 开启GPU以后 速度比 use-gpu=false更慢 HOT 3
- PPOCRv4_det检测模型训练,已经跑了350个epoch,hmean仍然维持在0.05-0.1不上升 HOT 8
- 运行demo报错 HOT 4
- batch 推理文本检测 HOT 4
- Mimalloc引起ppocr推理崩溃 HOT 2
- [Announcement] PaddleOCR PMC Officially Established
- How to disable .paddleocr directory creation? HOT 1
- GPU运行版面恢复未正常运行 HOT 4
- 使用合成数据集进行训练,数据集标注全数字训练,识别出汉字 HOT 5
- GPU运行版面恢复未正常运行 HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from paddleocr.