ujscjj

Hi, you can refer to this: https://github.com/ujscjj/On-Synthesis

The enc_dim is 256 in encoder, and the translate it to 64 by a linear layer before the dpt net.

I just updated the code, you can try it again.

Sorry for responding later. The hyperparameters match the configuration in the paper. On my machine, the model size is 2.69MB.

It's here: https://github.com/ujscjj/DPTNet/blob/master/others/optimizer_dptnet.py

I just updated the code.

@pchao6 谢谢你。（弱弱地问一句，我能加一下你的联系方式嘛。0.0 我的QQ：1372179162）

你好。不好意思，我没有实现过 attractor network 的代码。祝好。 ------------------ 原始邮件 ------------------ 发件人: "Yangjie55"; 发送时间: 2019年5月16日(星期四) 上午9:38 收件人: "pchao6/LSTM_PIT_Speech_Separation"; 抄送: "一棵树";"State change"; 主题: Re: [pchao6/LSTM_PIT_Speech_Separation] uPIT (#5) 学长，你有实现上面的那个danet这个方法嘛，我最近在做那个，参考的是https://github.com/khaotik/DaNet-Tensorflow 这个代码我用的timit数据集，实现不了唉，我看您跟吴学长有沟通过这个，不知道有没有实现呢。 另一个问题就是，我能用timit数据集去实现你的这个代码吗？因为我最近才学的这方面的东西，有很多东西不明白，生成txt那个地方我就不明白。。。。感谢你的回复！ — You are receiving this...

@pchao6 Thank you very much.

Ok. By the way, Xinlei Ren also winned the L3DAS21 challenge, and publiced their interactive demo at https://replicate.com/l3das/l3das22_challenge. I have experienced this demo, and it sounds not well. You can...