Closed seungwonpark closed 5 years ago
Train loss of initial implementation with nn.Conv2d converged at 6e-3.
nn.Conv2d
Now, I'm trying partial convolution padding scheme to replace naive zero-padding. Work in progress at pconv branch.
pconv
Unfortunately, it didn't work better. Hope to find out the reason in near future. Closing this issue until then.
Train loss of initial implementation with
nn.Conv2d
converged at 6e-3.Now, I'm trying partial convolution padding scheme to replace naive zero-padding. Work in progress at
pconv
branch.