Can’t reproduce your results in your cvpr paper

[yflv-yanxia]

I reproduced crnn+ctc and test it on IIIT5K+SVT+IC03+IC13 test database, got WER 0.153, which is same as the reported results in paper. I also reproduced crnn+ace loss, but only got WER 0.205 on the same test database, any advise? My environment: pytorch 1.2.0 batchsize 60 trained only on 8-million synthetic data released by Jaderberg iterations 1000k adadelta rho 0.9

[MiTeng0215]

I reproduced crnn+ctc and test it on IIIT5K+SVT+IC03+IC13 test database, got WER 0.153, which is same as the reported results in paper. I also reproduced crnn+ace loss, but only got WER 0.205 on the same test database, any advise? My environment: pytorch 1.2.0 batchsize 60 trained only on 8-million synthetic data released by Jaderberg iterations 1000k adadelta rho 0.9

I have the same results as you, and I want to know if you have any new progress.

[bjlgcxc]

it's hard for me to train crnn+ace loss to coverage, do you know why?

[zhangfengyo]

I reproduced crnn+ctc and test it on IIIT5K+SVT+IC03+IC13 test database, got WER 0.153, which is same as the reported results in paper. I also reproduced crnn+ace loss, but only got WER 0.205 on the same test database, any advise? My environment: pytorch 1.2.0 batchsize 60 trained only on 8-million synthetic data released by Jaderberg iterations 1000k adadelta rho 0.9

maybe some augmentation are used without mention in the paper