striversist

The following change temporarily fix the assert failure. @wanghaisheng ``` if (load_name != "") { clstm.load(load_name); trainingset.getCodec(clstm.net->codec); // Add this line } else { Codec codec; trainingset.getCodec(codec); print("got", codec.size(), "classes");...

@amitdo With experience, the more unicode codec you load, the slower the training process will be. So I don't think it's a best solution, no offence.

OK, looking forward to your solution.

Chinese has so many characters, we often train commonly used ones. But sometimes that's not enough. We want to add some uncommon characters, So the problem happens. If we retrain...

I think your [external codec file solution](https://github.com/tmbdev/clstm/issues/106#issuecomment-258894299) is good. We can prepare some codec for future use. @amitdo

The same problem. Ubuntu 14.04 OpenCV 2.4.13.2 CUDA: 8.0

这是目前在做的把DSO移植到Android上的项目，目前可以基于数据集跑，默认参数，10FPS左右

@dymymao 你好， 1. 10fps针对的是老款的OnePlus手机，目前主流中高机型应该能达到25FPS 2. 目前没有做特别的优化