Comments (8)
@haneSier 嗯嗯,谢谢你。现在已经收敛了,训练了20个小时后,loss为0.5左右,nepoch到了15.每个epoch运行122次。在训练的时间上有什么优化的方式吗?
准确率是0可能是因为开始就没找到收敛点,你要多试几次,这个东西能不能训练上去有一定的随机性,要初始点比较好才能够上去,学习率0.001,要是训练样本比较难,你可能得换个base model
from crnn_chinese_characters_rec.
可以不同长度,train loss降到一定程度才有预测的能力
from crnn_chinese_characters_rec.
@haneSier 嗯嗯,谢谢你。现在已经收敛了,训练了20个小时后,loss为0.5左右,nepoch到了15.每个epoch运行122次。在训练的时间上有什么优化的方式吗?
from crnn_chinese_characters_rec.
训练速度和你的设备有关
from crnn_chinese_characters_rec.
@haneSier 我是用的虚拟机+cpu,理解了。非常感谢您的帮助!
from crnn_chinese_characters_rec.
训练时loss一直在4.5左右震荡,我设置了一个极小的学习率,依旧震荡,无法收敛。请问这是什么原因造成的?我的数据集如下
from crnn_chinese_characters_rec.
之前训练的时候会将左右切割掉一部分,使得样本中字符占比更大,训练收敛了!现在的样本无法收敛,学习率和batch都设置的很小
from crnn_chinese_characters_rec.
Batch有条件就设置大一点,初始学习率如果很小的话很有可能无法收敛,固定batch,设置学习率观察收敛趋势,不明显就换一个学习率
from crnn_chinese_characters_rec.
Related Issues (20)
- how to set OWN_config.yaml without fine_tune from checkpoint HOT 1
- 训练自己的数据集,alphabets在进行decoding时提示字符找不到 HOT 1
- 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
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.