Comments (3)
lyu-dimo
commented on June 15, 2024
你好，根据我之前遇到的问题，可能造成的原因有以下几点：
1.卷积层数太少，深度不够（我是参考的谷歌的深度学习框架架构进行一些修改）；
2.训练的汉字字数太多，我是先从200个汉字进行训练的，如果训练全部汉字需要更改学习框架的代码（好像是在每一卷积层后增加了一句代码，不好意思，时间久远具体怎么修改已经忘记了，请google搜索）；
3.训练的次数太少，汉字识别相比于数字识别需要更多次的训练次数；
ps：我是从18年9月份开始接触学习的深度学习框架，从19年开始专注学习Java，以上原因有可能不准确，希望能给你一些提示，如果不能解决请前去google。
…------------------ 原始邮件 ------------------
发件人: "812618101"<[email protected]>;
发送时间: 2019年12月14日(星期六) 下午3:52
收件人: "integeruser/CASIA-HWDB1.1-cnn"<[email protected]>;
抄送: "Subscribed"<[email protected]>;
主题: [integeruser/CASIA-HWDB1.1-cnn] 你好！为什么我在训练的时候acc一直没有变化？损失也没有变化 (#1)
15个epoch之后，好像没有学到任何东西？
—
You are receiving this because you are subscribed to this thread.
Reply to this email directly, view it on GitHub, or unsubscribe.
from casia-hwdb1.1-cnn.
Jockey721
commented on June 15, 2024
你好，我怀疑是数据集处理有问题？
我试着加了卷积层，也改变了学习率，训练的次数的话，15个epoch，损失都没有一点变化的趋势，一直原地踏步。最后，我直接使用了你训练好的模型，然后用4-draw_results.py得到结果，但也是0.005（1/200）？
ps：非常感谢你能回答我的问题，我也是刚刚接触，想练练手
from casia-hwdb1.1-cnn.
lyu-dimo
commented on June 15, 2024
此模型是我检出别人的项目，我当初在进行调整时也并未进行上传。所以，很抱歉不能够给予解答，相信其他人的模型可以给你更好的结果。
ps:当初参考的Google深度学习框架是GoogLeNet，映像中好像和DepthConcat层有关系，配图是在网络中获取的，希望能给予你帮助。
from casia-hwdb1.1-cnn.
Related Issues (4)
- 兄弟，怎么拿标点符号啊 HOT 1
- 你好！请问数字和字母有没有对应的文件编号？ HOT 1
- Question about new format GNTX in CASIA database 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 casia-hwdb1.1-cnn.