Rudolph L

I checked that on my simple example with matching image with small db on 10 images - distance from nn_index stays the same with zero filling and without.

@ppwwyyxx yeah, sure. If in A i have 90 left rotated image, so in B it is the same, but night one. I can share my script that I`ve used...

Hi @danmic ! The same was for me. I guess it would be helpful to run also torch code and look what will be, as training "dynamic" wasn`t covered in...

@danmic as far as I remember, I think that through whole training relation between g_loss and d_loss was pretty high.