Tian Zhi

@txacuhan We cannot share the c++ version here due to our industry collaborations. I'm sorry for this. If you have any questions when you migrate the code into C++, please...

@iphone5solo Hi, please follow the instruction in README.md to get the two files. Thank you.

I am sorry. These images cannot be released due to their licenses. But we think today you can download enough scene text training data from the internet.

@txacuhan The errors happened because the program didn't support the CPU only mode then. We've updated it and it supports CPU only mode now. Please download it again. Thank you:-).

@striveallen Please make sure you compile caffe with Python support.

@bado-lee Maybe the metric you used considers as an error the case that the method merges several words into one line. You could upload your results here (http://rrc.cvc.uab.es/?ch=2&com=evaluation&task=1&f=1&e=2) and check...

@bado-lee Could you please try to upload the results on ICDAR official website (http://rrc.cvc.uab.es)? Thank you very much.

@zhcheng26 Thank you for your enquiry. You could refer to our paper.

@leaf918 Thank you for your suggestion. We will try to make it easier to use.

@chasonlee Good job! Thank you very much!