Hi, would you like to tell me why no softmax function used ?

Question

Hi, would you like to tell me why no softmax function used ?

Closed this issue 8 years ago · 3 comments

Hi, would you like to tell me why no softmax function used ? And would you like to share your cfg file ?

Answer 1 · 2017-04-26T06:29:48.000Z

Read the paper. There is a different architecture for score function layer. It's like calculating a tensor. This code is for actually test run. Author has clearly mentioned it :)

Answer 2 · 2017-04-26T06:57:21.000Z

Thank you for your answer !

Answer 3 · 2017-04-28T07:02:22.000Z

well it's like that. They needed to have a softmax function for class classification it will be costly. I had that problem too :D :D. It's not so clear. But if we find how they calculate P(Object) for each grid cell we might come up with an answer. I think those probabilities clearly align with IOU of bounding boxes.

…

On Wed, Apr 26, 2017 at 12:27 PM, YaoZhongtian ***@***.***> wrote: Closed #29 <#29>. — You are receiving this because you commented. Reply to this email directly, view it on GitHub <#29 (comment)>, or mute the thread <https://github.com/notifications/unsubscribe-auth/AQHCmsqKBkfzRG0ivlcguKVhG-fZoqBTks5rzurUgaJpZM4NE88L> .