Comments (7)
我有过这样的问题,我的设置是对的,你可参考一下。
from crnn.caffe.
为什么inference阶段 设置use_global_stats: false 重新计算 而不是用已经训好的参数? @yalecyu
from crnn.caffe.
我发现如果deploy里面的use_global_stats设置为false,是有识别结果,但是使用提取特征extract最后一层softmax特征获取的最大概率对应的类别和使用识别recongine识别的结果有时候会出现不一致。
如果deploy里面的use_global_stats设置为true,extract和recongine获取的概率分布一致了,但是都是错误的,把所有的类别都预测为同一类,比如都预测为空格是。所以我想问,这个use_global_stats应该怎么设置。
from crnn.caffe.
@871699406 @loliod @chendan1988-1994 可能真的有错误,非常抱歉,在我最新版的模型上,我已经修复了BatchNorm的问题。我的理解是,在训练的时候使用false,来学习参数,测试的时候true,来使用学习到的参数。
from crnn.caffe.
好的好的,谢谢您。虽然出了一点点小问题,但是您的代码真的让我学到了很多东西,对我的帮助也很大,再次感谢您。
from crnn.caffe.
@yalecyu 可否告知你是怎么修改的BatchNorm的问题?具体修改了哪里?对这个问题比较感兴趣
from crnn.caffe.
@871699406 最新的prototxt已经修改了BN层的配置
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.