Git Product home page Git Product logo

emotion_classifier's Issues

关于batch_siz,validation_steps,steps_per_epoch的关系

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

关于单张图片的预测问题。

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。

作者你好,有关test结果问题向你请教

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!!

hi .sry to bother u again~

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~

Kernel dead

运行模型测试部分的代码时,kernel就dead了

关于emotion_classifier的问题

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!

测试 confuse matrix 和 测试集acc

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

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo 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.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.