Skip to main content

Density training with PatchGAN loss

Trained with Hinge Loss Discriminator number of channels 3->64->128->256->512 (spatial dimensions at the end = 16x16) No multiiterations for Discriminator Same learning rate
Created on December 21|Last edited on December 21

Section 1

Add markdown, images, and LaTeX\LaTeX




Select runs that logged density-dloss
to visualize data in this line chart.
Select runs that logged density-gloss
to visualize data in this line chart.
Select runs that logged density-f1
to visualize data in this line chart.
Run: data/gumble_patchgan_v0.t7
0