Comments (15)
sorry,the lstm_layer.cpp has not changed .I mistake it with other file.
from crnn.caffe.
@871699406 I read your message. I always say, I'll reply you.But in the last few days there are many things on hand, and I always forget about the thing to reply you.It is good to solve this problem.More communication, sorry again.
from crnn.caffe.
I am glad to have your reply.
And you haven't answer my question yet. 0.0
Did you just add the continuation_indicator_layer.cpp(.cu) and ctc_entrypoint.cpp(.cu) and ctc_loss_layer.(.cu) to the original caffe ?
from crnn.caffe.
@871699406 Yes.When some layers does not have,I added them.You can try.
from crnn.caffe.
看你的名字好像是**人,不知道能否用中文交流?
from crnn.caffe.
@871699406 你运行模型,缺失的层,通过读我这个caffe,进行补充就可以了。怎么添加新的Layer你可以通过网上的很多文章学习。我试过补充过这些层,是可以的。
from crnn.caffe.
嗯嗯,我现在具体有两个问题
1.你的这版caffe具体你新加了哪些层?
2.你给出了crnn_captcha.caffemodel这个参数,这是用captcha重新训练的么?还是你用什么别的模型fine tuning得到的?训练集多大?准确率有多少呢?
from crnn.caffe.
我忘记了我添加了什么层,我从其他项目移植过来。
1.你可以通过运行模型,查看缺失那些层,我移植过这个项目,去合并到别人的项目里,是没有部分层,挺简单的。
2.crnn.prototxt是训练模型文件,你可以看一下。我没有fine-tuning,生成了10w的数据的时候,准确率可以到99%+。这个crnn是小的网络,收敛挺快的。
from crnn.caffe.
好的,谢谢你的回复哈
我用自己的训练集跑了一下,收敛到85%,训练集2W左右,看来还是扩充数据是王道啊,哈哈~
from crnn.caffe.
可以训练中文吧?
from crnn.caffe.
@wanhaipeng 可以,但是训练样本要够,我的模型就是训练样本有点少,你可以扩充训练样本试一下,具体方法在另一个issue里有
from crnn.caffe.
@871699406 好的
from crnn.caffe.
@871699406 您好,你中文训练集格式是怎样的呢?是一个jpg对应着一个txt,还是按照这里的captcha图片格式?
from crnn.caffe.
@weiweili123 是对应的captcha格式,你也可以一个jpg对应着一个txt,只要在标签转换的时候能读入就行,这不重要,重要的是标签转换这一步要准确不出错
from crnn.caffe.
好的,谢谢你的回复哈
我用自己的训练集跑了一下,收敛到85%,训练集2W左右,看来还是扩充数据是王道啊,哈哈~
你好,我训练时accurccy为0.99,但是用图片测试时显示的结果为- - - - - - - - - - - - - - - - - - - - - - - - - -
from crnn.caffe.
Related Issues (20)
- Wrong accuracy when I change test_iter HOT 1
- 测试结果出现了很大问题 HOT 9
- 测试例子出现问题 HOT 5
- hello,麻烦咨询下我这边有个维度不匹配的情况 HOT 11
- 标签问题 HOT 4
- ContinuationIndicator出自哪里?
- your model doesn't match to your deploy.txt HOT 4
- 图片是不是必须这个格式,多一点边框都不行吗? HOT 1
- 自制数据集,过拟合的问题 HOT 7
- accuracy is 0 HOT 5
- example core dump
- 测试结果的问题 HOT 3
- test_accuracy和模型实际测试的值不同
- Alphabets in label's questions HOT 2
- 将CNN换成densenet结构后,BN层设置问题
- CNN结构替换成denseNet时遇到的问题
- make fail with protobuf/stubs/common.h not found
- 训练你的代码出现维度不匹配
- check failed: registry.count(type)==1(0 vs 1) unknown layer type:
- 你好,训练自己数据的时候准确率和loss都为0 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 crnn.caffe.