Results

[teddyjkwang]

Hi,thanks for the work.
Did you try on the dataset and how is the accuracy?

[LevinJ]

Hi , @seragENTp , I am thinking of implementing that paper in tensoflow too. So am wondering if you have repeated the result in that parper? Thanks.

[lmolhw5252]

Hi, I use your code but it cannot convergence,and loss is always 2.29-2.3.
What's my problem? I don't change anymore.

[teddyjkwang]

@lmolhw5252 I found the same problem.I thought the way to define the target of cross entropy is not right but not sure

[lmolhw5252]

@SwaggyK93 Can you fix it?

[LevinJ]

Hi @SwaggyK93 , @lmolhw5252 , just thought you might be interested, I implemented the model in tensorflow and was able to reproduce the paper result.

Here is my code implementation.

[teddyjkwang]

@LevinJ
THANKs so much for that!!

[teddyjkwang]

哈哈谢谢老师 我会认真学习的

[lmolhw5252]

@LevinJ 非常感谢！您好我想请教您个问题，这篇论文中只是使用了3个数的MNIST数据集，并且设定切片个数为3，可是STN-OCR一文中，也是引用了这个方法，但是那篇论文好像没有切片个数的限制，请问您对这个有研究么？
“STN-OCR: A single Neural Network for Text Detection and Text Recognition”这个是那篇论文的题目。

[LevinJ]

你好，我大致看了下论文，STN-OCR也是用了固定数目的切片。 文章有提到将来可能会研究由模型自动确定切片数目（或者说textline/characters 数目）。 你可以查看一下 "5.Conclusion"部分。

[lmolhw5252]

@LevinJ 非常感谢您！！