PatchGAN output channels set equal to in_channels? Change it to 1 about ganslate

[surajpaib]

Took a look at it and yeah makes sense. I'd suggest adding out_channels with a default of 1 and then in_channels as well, rather than hard coding out channels to one.

@cnmy-ro Time for your first PR to master I'd say

[ibro45]

ah fuck that's true, i messed it up, sorry... @surajpaib important for your current experiments.

[ibro45]

where do you think having patchgan with out channels different than 1 would be useful? i think it should always be one, no?

[cnmy-ro]

I think it's always 1, as well. Just checked the paper too. As I understood, a regular D outputs just a single scalar probability, but PatchGAN outputs one for each spatial patch of the input. This spatial patch may or maynot contain multiple channels

[cnmy-ro]

I'll implement the new dataset and create a PR by tonight. Was just testing things in a Colab notebook (for which I took the Unet2D and PatchGAN2D code from midaGAN) coz don't wanna waste Aachen Cluster's compute

[surajpaib]

Yeaah didn't realize it affected my experiments since its a no break bug. It's now computing LS on 3 channel output maps, interesting. I wonder how much it affects things

where do you think having patchgan with out channels different than 1 would be useful? i think it should always be one, no?

I think its better to define it as a parameter to make things more explicit. Just a suggestion though ofcourse.

[surajpaib]

Good catch @cnmy-ro

[ibro45]

Yeah, great catch!

[cnmy-ro]

Thanks! A similar, but different thing - earlier while experimenting with Cityscapes dataset I added an additional parameter "out_channels" for Unet2D and Unet3D. I was trying inputs and outputs having different channels, but out_channels was hard-coded to be equal to in_channels then. I'll create another issue for this.

[cnmy-ro]

Nevermind with the new issue actually. Just wanted to mention this change