GabrielLin

Thank you @siddharthasahu . I suggest adding an option for saving the last n epoch of model.

OK. Thank you. I think this suggestion can be an enhancement in the further version.

What about the progress? I think it is a great function. Thanks.

What is the value of your WER? Do you train your own model with your data?

This is a great idea.

I have the same situation with Tensorflow 1.3.0 and Keras 2.0.5. @alex-mocanu , @mjdietzx , could you please tell me how long you trained the model? Thanks.

Thank you for your reply. That project is useful for learning how to use regression of Caffe. The reason why I want train_val.prototxt and solver.prototxt in this project is that...

Thanks. I strongly hope that you can find it.

Dear qiexing, have you find the prototxt files? Thanks.

Thank you very much. You are a really a person.