Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

demo/mnist的Tutorial #884

Closed
dayhaha opened this issue Dec 14, 2016 · 7 comments
Closed

demo/mnist的Tutorial #884

dayhaha opened this issue Dec 14, 2016 · 7 comments
Assignees

Comments

@dayhaha
Copy link
Contributor

dayhaha commented Dec 14, 2016

一直有一个问题,mnist作为一个比较简单的例子,为什么只是在代码里面有,而在文档里面不作为demo示例进行开放呢?
tensorflow https://www.tensorflow.org/tutorials/mnist/beginners/
mxnet http://mxnet.io/tutorials/python/mnist.html
tensorflow和mxnet都把mnist手写字识别作为第一个例子来让初学者入门,而且尽量详细的将一些机器学习相关的初步知识。两者都是先用MLP训练,然后再用CNN来提高效果,让初学者体验CNN对图像识别的一个显著提升作用,而paddle里面为什么只有比较高端的vgg_net呢?这一块是不是可以添加一下呢?

@luotao1
Copy link
Contributor

luotao1 commented Dec 14, 2016

mnist的tutorial正在考虑加,@dayhaha 你可以加一份么?

@luotao1 luotao1 changed the title mnist为什么在文档里面不作为demo开放 demo/mnist的Tutorial Dec 14, 2016
@dayhaha
Copy link
Contributor Author

dayhaha commented Dec 14, 2016

那我领这个任务,尝试丰富这个demo吧。

@luotao1
Copy link
Contributor

luotao1 commented Dec 14, 2016

可以先写中文文档。

@dayhaha
Copy link
Contributor Author

dayhaha commented Dec 14, 2016

那我能先写mnist的MLP和CNN的paddle实现,提交代码,review通过了再写文档么?

@dayhaha
Copy link
Contributor Author

dayhaha commented Dec 14, 2016

demo里面只有vgg_16_mnist.py,但是tensorflow和mxnet都把这个作为一个经典例子,先用基础的模型,分类准确率大概为92%,然后再用CNN,分类准确率就上升到了99%,我是觉得我们是不是可以像那样丰富一下?

@qingqing01
Copy link
Contributor

@dayhaha 支持,我觉得这样挺好的, 使用简单一些网络,训练速度也快,适合用户学习。

@luotao1
Copy link
Contributor

luotao1 commented Apr 28, 2017

由于PaddlePaddle Book中更新了"识别数字"的中英文教程,因此该issue就close了。

@luotao1 luotao1 closed this as completed Apr 28, 2017
lizexu123 pushed a commit to lizexu123/Paddle that referenced this issue Feb 23, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

No branches or pull requests

3 participants