fengqiyun

hello,Mauker1.I'm sorry to come down to your homepage and ask such a question。I'm replicating segan's experiment, the paper is SEGAN:SEGAN: Speech Enhancement Generative Adversarial Network, I saw your message on...

Have you successfully replicated the experiment？I find that the g_adv loss is always 1 in training.And the loss seems to be different from the picture provided by the author.Can you...

After the final training, how much are d_rl_loss,d_fk_lossg_adv_loss and g_l1_loss respectively?I found that the loss of the training discriminator is very small, basically about 0.0005