Comments (10)
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
from ganslate.
ah fuck that's true, i messed it up, sorry... @surajpaib important for your current experiments.
from ganslate.
where do you think having patchgan with out channels different than 1 would be useful? i think it should always be one, no?
from ganslate.
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
from ganslate.
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
from ganslate.
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.
from ganslate.
Good catch @cnmy-ro
from ganslate.
Yeah, great catch!
from ganslate.
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.
from ganslate.
Nevermind with the new issue actually. Just wanted to mention this change
from ganslate.
Related Issues (20)
- Windowed images not displayed correctly in tensorboard
- Switch to monai's `decollate_batch`
- Functionality documentation: Is the core functionality of the software documented to a satisfactory level (e.g., API method documentation)? HOT 1
- Add more functionality tests: HOT 1
- make default imagedataset have different behavior for train vs val/test modes HOT 4
- metrics calculation not working for batch_size > 1
- Better logging names for losses, metric, G and D, and visuals
- metrics all over the place in GAN implementations HOT 1
- Val-Test metrics need to work accurately across batches and across data points HOT 4
- Add warning for when dataset size is smaller than number of processes in DDP * batch size HOT 1
- Figure out logging for multimodal images
- Make CycleGAN's separate channel config cleaner and more readable
- Document + support framework for fine-tuning on a different dataset HOT 2
- Out channels missing in PatchGAN 3D HOT 1
- Volumetric probability map based PatchSampler HOT 5
- Add structure-constrained GANs to the list of available GANs
- separate out medical utils
- CLI tab autocompletion not working
- Restructure docs to separate package overview from tutorials
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from ganslate.