Comments (5)
Hi, 新版本的测试代码test.py文件有bug,这是其他同学提交PR时产生的,还未经过测试,可使用PR之前的版本训练和测试。另外精度低是不是你的resized的widht和height设置和训练时的配置不同.
config_lmdb.json中n_class已经改为读取key.txt并自动计算出类别数了,见here
论文中精度指标是Case_ins.
from master-pytorch.
为什么我验证时有95%的正确率测试时不到56为什么高和宽都一样
from master-pytorch.
Hi, 新版本的测试代码test.py文件有bug,这是其他同学提交PR时产生的,还未经过测试,可使用PR之前的版本训练和测试。另外精度低是不是你的resized的widht和height设置和训练时的配置不同.
config_lmdb.json中n_class已经改为读取key.txt并自动计算出类别数了,见here
论文中精度指标是Case_ins.
pr之前的版本确定行吗,可以公开模型吗
from master-pytorch.
可以分享下测试数据集吗?
from master-pytorch.
说明一下,文字识别在公开的数据集上的指标是不区分大小写(Case ins)的,这是公开论文的通用做法,请阅读相关论文。代码中在训练时为简单打印的是不区分大小写的指标。而使用test.py文件推理时为了更通用,打印了两种指标,分别是区分大小写的(Sequence Accuracy)和不区分大小写的(Case_ins)指标。希望解惑。如果为了对齐论文的指标,请看Case_ins的指标。
from master-pytorch.
Related Issues (20)
- 有尝试中文效果吗 HOT 3
- debug模式进行单gpu训练报错
- train error
- 和paddleocr相比
- 感谢开源,请问有谁可以解释下这行代码的意思?谢谢!
- 这个标签实在是有点迷,大佬可以帮忙解释下? HOT 1
- 长文本识别效果如何改进? HOT 1
- 预测问题
- test.py运行报错
- pretrained_model
- MASTER HOT 1
- 对比SATRN
- inference time
- 运行错误
- 测试
- 有偿 HOT 2
- master 有人复现到论文的结果吗
- 多行数据怎么标注呢?识别结果解码出来怎么分开呢
- Are the download links of the trained checkpoint weights provided?
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 master-pytorch.