Closed vztu closed 3 years ago
Hi, vztu, Thanks for your attention to HINet. We did not use different parameters for each task, and the number of HINet would be about 88.7M as we made a tradeoff between time/space complexity.
Hi, Thanks for your prompt reply!
I am wondering could you also append the parameters for MPRNet for each task as well?
Hi thanks! I'll check out their paper
Hi, thanks for sharing this great works! It seems MPRNet uses different parameters for each task, (like channels=40, 64, 80, etc). Could you please add an extra column in Table 4 showing the exact parameters for each model? I really appreciate if you can do so!