shillyshallysxy / emotion_classifier Goto Github PK
View Code? Open in Web Editor NEWemotion classifier based on kaggle fer2013
emotion classifier based on kaggle fer2013
你好,首先非常感谢您的无私分享,我的问题就是为什么识别率之和的结果不等于1呢?
博主您好;
我想请问一个问题,
若是我想在ubuntu上使用这份代码,那有些什么地方是需要修改和注意的吗?
期待您的回复,谢谢~
您好我想问您的原码中nb_epoch,batch_siz,validation_steps的关系,您说批尺寸迭代步数是48200,也就是25600,为何是25600?FER2013的训练集应该只有28709个图像,还有看您的源码里写的validation_steps=2000,为何是2000不是200?
另外这里:steps_per_epoch=800/(batch_siz/32),为何这样取steps_per_epoch?期待您的解答
你好,很感谢博主你的无私分享。本人刚刚学习机器学习,我想请问一下预测单张图片情绪的py如何改为要预测图片的地址?
希望能得到你的回复,谢谢你。
Hey
I read your comment here
https://github.com/amineHorseman/facial-expression-recognition-using-cnn
You said you have updates manuscript of their code.
Can you send me?
[email protected]
能否提供个百度网盘链接?谢谢!
针对fer2013数据集,在您的tensorflow版本emotion classifier上进行了训练(没有改动代码)训练过程中的测试结果准确率大概在65%上下浮动,迭代了20000次之后,进行测试结果准确率只有65%左右,并没有达到70%.请问您的训练代码是否和该上传代码有所不同,可否提供模型下载链接呢?谢谢!!
sry .i didnt install chinese input-method on my ubuntu OS so that i write down my question in ENGLISH.
i run your code successfully on ubuntu os, and i tested ur model. the outcomes are as follows
{'angry': 1.680927, 'disgust:': 0.024156317, 'fear': 0.38532764, 'happy': 0.37007406, 'sad': 0.30601713, 'surprise': 0.08675081, 'neutral': 0.146747}
Emotion : angry
{'angry': 0.2911712, 'disgust:': 0.044982724, 'fear': 0.24095652, 'happy': 1.2809961, 'sad': 0.17451024, 'surprise': 0.19956648, 'neutral': 0.7678167}
Emotion : happy
{'angry': 0.85339236, 'disgust:': 0.18872109, 'fear': 0.7736851, 'happy': 0.21916914, 'sad': 0.16908921, 'surprise': 0.25328648, 'neutral': 0.5426566}
Emotion : angry
im so confused that why the sum of these probabilities is not 1?
im looking forward to ur early reply .thx~
运行模型测试部分的代码时,kernel就dead了
你好,首先谢谢你的回复,现在不得不再次询问你,就是那个keras的单张图片预测的py程序里修改为预测图片或预测文件夹的路径怎么修改呢,改哪里?
希望您能够再次回答,谢谢!
Shilly你好, 在测试你提供的模型时,运行
python confusion_matrix.py model
之后得到的测试集acc只有55.586% 并不能达到你图片上的~70% 是模型上还需要一定的修改吗
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.