MiTeng0215

@zhouyuangan Have you trained this model? I trained with two GPUs overnight and only trained 12% of one epoch.

How about the effect of detection and recognition？ 发自我的 iPhone > 在 2020年2月5日，17:08，Yg Zhou 写道： > > Yes, I did, but it's very slow. > > > > 发自我的 iPad >...

> Hello, > > While I am training the model I am getting negative Recognition Loss values. Is there any way to fix this issue? me too. I wonder if...

> I have the same error too, have you solved this problem? > Maybe cudnn version is wrong. > But which cuda and cudnn version are right? My env: tensorflow-gpu=1.6.0...

> 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...

@LJXLJXLJX Have you solved it?

> I pretrained a model using ctcloss and it works well. Then I loaded the weights and continued to train with the aceloss. The losses seemed to be coming down,...