52
Awlex
7y

Person: I see you're training your neural net. How's it doing?
Me: Well...

Comments
  • 1
    lol..bruh..what net is that? architecture
  • 2
    Soooo, gain?
  • 3
    @bdhobare a lstm->fullyconnected->regression. Note that I wrote the loss function special. Nevertheless, you should not be able to get some negative when working with positive numbersand not a single negative ones, since you work with distances.

    I must have revolutionized mathematics
  • 0
    @Kimmax sadly no, performed even worse that the previos one
  • 0
    I just hope this works faster than a month for your sake 😶
  • 1
    @Awlex use RELU before the regression layer to remove negatives
  • 0
    count your losses
  • 0
    I wouldn't mind some negative loss...
  • 0
    Doesn't look like it is converging
Add Comment