Open bobo0810 opened 4 years ago
Thanks for your working! I have some questions:
- That reduction ratios R=8 is the best trade-off in the paper , but the code defaults to 4, so why?
- In the 800,000 person face classification task, what would you recommend the value of R? @Islanna Thank you again~
hello,use dynamic relu in your task ,acc is ok?
Thanks for your working! I have some questions:
- That reduction ratios R=8 is the best trade-off in the paper , but the code defaults to 4, so why?
- In the 800,000 person face classification task, what would you recommend the value of R? @Islanna Thank you again~
hello,use dynamic relu in your task ,acc is ok?
I haven't experimented...
Hi!
The main reason is that I mainly used DyReLU to experiment with Speech-To-Text task. Sound's models and preprocessing are a little different from models for images. For example, often conv1d is used instead of conv2d.
So, the reduction ratio = 2-4 is optimal for sound. If you want to work with images maybe you should change it to 8 as in the paper.
Hi!
The main reason is that I mainly used DyReLU to experiment with Speech-To-Text task. Sound's models and preprocessing are a little different from models for images. For example, often conv1d is used instead of conv2d.
So, the reduction ratio = 2-4 is optimal for sound. If you want to work with images maybe you should change it to 8 as in the paper.
Thanks reply!According to the paper, ratio = 8 is the best trade-off. Although ratiobn=4 works better, but it is very weak. Therefore, for better performance, choosing ration=4 is a suitable choice. Is it right?
Thanks for your working! I have some questions: