ujscjj / dptnet Goto Github PK

Thanks for sharing your codes. I'm wondering if this enc_dim is 64 (as in your paper) or 256 (as in the code page https://github.com/ujscjj/DPTNet/blob/master/dpt_net.py).

Hi, I am curious about the importance of the proposed improved Transformer layer compared to the standard one (w/o the positional encoding). But I couldn't find the related information in the paper.

I implemented DPTNet using shi's code.
But I got 2.8M model size.
how can i reduce model size to 2.69M?

how to set the training learning rate?

I am a student studying speech separation. I sincerely want to communicate with you about the in-depth application of transformers in speech separation. Can you give me a contact information?

Hello, could you share the LS_2mix datasets to me?

Hi, have you been planning to share the entire code recently？