Git Product home page Git Product logo

Comments (5)

zhaipro avatar zhaipro commented on May 30, 2024

其实,我想知道更有统计数理论的参数。但是,我的能力…

看来我需要把埋在床底的书找出来了。

from easy12306.

zhaipro avatar zhaipro commented on May 30, 2024

让统计学数据集做训练集,让此数据集做验证集

Epoch 100/100
8264/8264 [=] - ... - loss: 0.2421 - acc: 0.9211 - val_loss: 0.3360 - val_acc: 0.9462
[0.2166585269566813, 0.9507376632185858]

等等,只有在验证集上的正确率超过96.7%才算有进展,对吧

我开始觉得自己搞错了,卷积神经网络的用途在于面对前所未见的样本,这是无论如何统计学都做不到的。

from easy12306.

zhaipro avatar zhaipro commented on May 30, 2024

a3

~$ python3 main.py a.jpg
26
0 0 32
0 1 8
0 2 57
0 3 4
1 0 45
1 1 26
1 2 75
1 3 38

[19 78 73 10 26 38 26  8]

机器学习后的模型可以识别前所未见的图片,其中的蒸笼和创可贴都识别正确了。也许统计学可以在见过的图片中有98%的识别率,而学习后的框架则具有在无限空间中有94%的识别率。哦对了,那个文字的书写方式也是卷积神经网络在学习时没有见过的。

from easy12306.

zhaipro avatar zhaipro commented on May 30, 2024

那我就坐等新图出现吧

from easy12306.

zhaipro avatar zhaipro commented on May 30, 2024

这里的数据集用于测试,得出的结果:
统计学专家的正确率:0.9422140966882884
从统计学专家哪里学来的深度学习模型的正确率:0.9811081335640064

可以以此证明学习后的神经网络具备识别前所未见的实力吗?

from easy12306.

Related Issues (20)

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.