Where is the discriminator network parametrized by omega?

[~litlep-nibbyt]

Hi,

I was looking through your code, namely here: https://github.com/rdevon/DIM/blob/bac4765a8126746675f517c7bfa1b04b88044d51/cortex_DIM/functions/dim_losses.py#L109 and noticed that in the docstring it states that the losses take the feature maps l and m directly. However, in the paper, it is stated that the losses take the score that the discriminator gives to the feature maps. In the implementation where does the forward pass to the discriminator networks occur?

[Yassine]

This is a second and more efficient way of computing the neg / positives, check the appendix A2, they go through both ways, with a discriminator and with a non-linear embedding.