Comments (2)
It maybe training is not converged. 100K iterations maybe work. Specifically detection loss should be around 0.005 and recognition loss should be around 0.5.
And I'm sorry, the model I have trained can not get ideal result, F-score is only 30 on ICDAR2015 testset.
I'm still debug the code, If you're in a hurry, you can try another implementation. :)
And I think pretrained on Synth800K is important, since recognition needs a lot of data
from fots_tf.
Oh, Okay.
from fots_tf.
Related Issues (20)
- 识别结果丢字情况
- why so slow? HOT 16
- How to evaluate FOTS with an F_score HOT 2
- Results are not as good as the pretrained network after a train with the pretrained option.
- Train only the recognition branch HOT 8
- 请问如何识别中文字符? HOT 18
- InvalidArgumentError (see above for traceback): assertion failed: [width must be >= target + offset.] [[node RoIrotate/while/crop_to_bounding_box/Assert_1/Assert (defined at /ext/wd_test/FOTS_TF-dev/module/RoI_rotate.py:113) ]] [[node RoIrotate/while/Identity (defined at /ext/wd_test/FOTS_TF-dev/module/RoI_rotate.py:119) ]] HOT 1
- 请问一下有人跑通过代码吗,代码的运行环境是什么? HOT 2
- Specify epochs? HOT 3
- ValueError: The passed save_path is not a valid checkpoint: SynthText_6_epochs/ HOT 3
- Cannot compile lanms HOT 1
- change number of classes?
- about loss HOT 2
- Pretrained model link not working HOT 2
- Train model long line. HOT 1
- Low loss but low accuracy HOT 3
- 使用360万中文数据集(Synthetic Chinese String Dataset)训练
- 测试识别分支
- 顺时针标注和逆时针标注的数据都能成功训练吗
- [Invalid argument: assertion failed: [width must be >= target + offset.]]
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 fots_tf.