Comments (6)
为啥不合理?只要你的文本不是太长(比如宽度超过2048)。padding不就浪费了,为啥不选用其他图像侧的backbone呢?
from trocr-chinese.
from trocr-chinese.
我理解应该是大量数据预训练的前提,可以把变形的文字也看成一种字体,学习过了就可以准确预测
from trocr-chinese.
resize到固定尺寸必然会导致文字信息产生变形。 发自我的iPhone
…
------------------ 原始邮件 ------------------ 发件人: lywen @.> 发送时间: 2022年4月9日 21:19 收件人: chineseocr/trocr-chinese @.> 抄送: archwolf118 @.>, Author @.> 主题: Re: [chineseocr/trocr-chinese] 现在trocr最大的问题就是这个384384的预处理 (Issue #3) 为啥不合理?只要你的文本不是太长(比如宽度超过2048)。padding不就浪费了,为啥不选用其他图像侧的backbone呢? — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.**>
形变有啥关系呢,预训练就让模型适应了这样的变化,相当于模型进行了空间映射。
from trocr-chinese.
任何算法都不是全能的。如果觉得此方法不好,可以选择其他算法,不要因为此项目让自己不愉快。
from trocr-chinese.
超长的文本,其实也是可以识别出来的,roberta是支持最大510个字符(除去s,/s),只是seq2seq方式会超慢而已(如果自己场景全是超过2048像素,ctc方式也需要很大的显卡才能训练得很好)。这里探索的是用一些transformer的方式去解决比如弧形文字、不规则文字、多行文字的端识别方法。
from trocr-chinese.
Related Issues (20)
- 交个朋友? HOT 1
- 使用自定义vocab.txt HOT 2
- 关于印章识别 HOT 3
- How to generate the our own pretrained weights?
- 请问预训练模型使用的数据 HOT 3
- ICDAR2023端到端印章名称识别 HOT 1
- 多行文字识别问题
- Prompt Learning相关问题
- 修改processor后重新训练
- onnxruntime 转换报错 HOT 4
- 打印文本识别 HOT 1
- Tensorrt部署 HOT 1
- RuntimeError: CUDA error: device-side assert triggered! Solve!!!
- 预训练
- 您好,请教一下您给的数据集的实例的问题 HOT 1
- 印章文字识别模型什么时候开放下载 HOT 2
- 长文本中相同的文字识别错误,但是切割后都可以识别对 HOT 1
- 大佬们谁有表格数据集?
- 印章数据集百度网盘下载链接失效
- 识别多行文本 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 trocr-chinese.