Issue about the Loss

[wbhu]

Issue about the Loss

[wbhu]

Hi @NathanielNguyen11 ,

In my machine, the converged loss is about 3.4 too. And, the converged loss is about 1.2 in the original matconvNet implement. I am trying to find why, but it may be slow since I have something else having to do. If you find the reason, welcome to pull a request.

thanks.

[edogawachia]

i changed the activation function in layer which is originally relu to leaky relu, and the loss converges to about 1.2. Hope that helps you~ @crisb-DUT

[OpenCv30]

Hi,
I am trying to train this model using my own noise data but i am seeing same issue. Even after running for 12hrs on GPU but final error came to only 3 with Adamoptimser and 2.5 using AdamDelta optimiser. Please suggest if you the actual error. As it is mentioned that chnage relu to leaky-relu to get error of 1. But is it sufficient to get performance comparable to matlab performance with such trained model.
Regards,
Sumit Jha

[wbhu]

Thanks @edogawachia. I will have a try if there is any free time.

[lizhiyuanUSTC]

@NathanielNguyen11 I noticed that the last conv layer don't use BN and relu in paper, and I changed the code so the training loss decreased less than 1.2.

[wbhu]

Thanks @lizhiyuanUSTC ,

You are right. I have merged your pull request. Now I am training the new model.

[wbhu]

Hi all,

I have trained and tested the new model, and it has the same Gaussian denoising performance at noise level 25 on BSD68 test set.

Thanks for all of your help.