MichelleYang2017
MichelleYang2017
The version of TF is 1.9,br_count is a global real.
Now I am also facing the same issue.
Both Slow. I am so sad
I want to know whether there is model trained.If I have a picture,I can load the model and denoise the picture instead of training by myself.
> You can find it in README. I read REANME yesterday. Your code can product some nosied images and denosied images but this is a process you made.But I have...
> Please clarify what you did in command line level. If I analysis the nosied data's distribution parameters ，when I use your weights to predict a noise images to clean...
I guess that my images is gray that it doesn't work.If I want to denois images I need to train weights by myself what do you think?
That is to say,delete the samples which the utterance starts from zero and ends also at zero?
Hello，I'd like to reimplement your paper code completely, I just want to know will the code about the extract feature and add noise be open?Thank you
eras使用‘accuracy’作为metrics时，默认调用的是metrics.py里的accuracy(y_true, y_pred)函数吧，当指定为metrics.categorical_accuracy才用的是categorical_accuracy函数吧