Comments (10)
haneSier
commented on May 24, 2024
可以先保存模型，换个learning rate
from crnn_chinese_characters_rec.
haneSier
commented on May 24, 2024
这些参数是我加了我自己生成的数据finetune的参数，如果你有条件，batch size 大一点会更好
from crnn_chinese_characters_rec.
Aurora11111
commented on May 24, 2024
你是说降低学习率不断调试吗?
还有就是我看你的github下又多出一部分datagenerator,你是在调参的时候还加了数据?
from crnn_chinese_characters_rec.
haneSier
commented on May 24, 2024
嗯，这个 data generator 是将模型调到我自己应用场景加的数据
from crnn_chinese_characters_rec.
haneSier
commented on May 24, 2024
嗯嗯对，标签和图片路径
from crnn_chinese_characters_rec.
haneSier
commented on May 24, 2024
我在训练的时候，只要设置一个合适的学习率（当时我用的应该是0.001），loss能降到2左右，然后再换小一点的
from crnn_chinese_characters_rec.
Sierkinhane
commented on May 24, 2024
https://github.com/Sierkinhane/crnn_chinese_characters_rec/blob/master/test_images/4.png 这是我刚才跑了一下代码的结果，
from crnn_chinese_characters_rec.
haneSier
commented on May 24, 2024
有加上自己的
from crnn_chinese_characters_rec.
haneSier
commented on May 24, 2024
嗯嗯，在原来模型跑的，主要是看个效果，
from crnn_chinese_characters_rec.
haneSier
commented on May 24, 2024
没有，第一个是每隔几样本显示一次，第二个是每隔多少步验证一次
from crnn_chinese_characters_rec.
Related Issues (20)
- 这个网络是否采用了GRU？
- 尝试了安装这个包也不行，请问要怎么处理
- 字符位置预测问题
- demo和validate结果不一致 HOT 1
- export to onnx issue
- The disk data is full, and the GPU operation efficiency is very low
- ctc loss error
- 作者提供的数据集为什么只有156万多，没有360w HOT 1
- 如何进行测试呢？
- Test loss: 5.1653, accuracy: 0.0000. I tried to train 2 images as own data, accuracy is always 0.0000. What is the probem? [email protected]
- 过拟合问题
- 训练loss不降，acc=0, 预测为空 HOT 2
- 训练速度太慢了，怎么解决？？
- 怎么使用多卡训练 HOT 2
- log_softmax HOT 1
- demo里识别不了车牌和验证码，只能识别截图的字 HOT 3
- loss一开始就0.5左右，后续能降到0.00几 HOT 2
- mm
- 数据集问题
- 修改完8P后loss不收敛
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 crnn_chinese_characters_rec.