Hi, Thanks for sharing your code. I am trying to understand the logic behind using dimensions of the 'src loss' function for the discriminator. So, in solver.py, 16x1x2x2 dimensional output is used for 'src loss'. 16 is batch size but why is it 2x2? Why there is no activation after this?
Hi, Thanks for sharing your code. I am trying to understand the logic behind using dimensions of the 'src loss' function for the discriminator. So, in solver.py, 16x1x2x2 dimensional output is used for 'src loss'. 16 is batch size but why is it 2x2? Why there is no activation after this?