Comments (5)
Hi,
If you don't want to use class labels, how about using GAN without condition (gan_train.py
). However, I believe it performs best on datasets where their images are sharing similar features/structure. As you see we trained on bedroom dataset. There, you can create your own noise (incorporating noises etc.) and the model should generate different images.
Does the dataset you want to train contain so many different things (e.g. airplanes, flowers, different animals in one dataset)?
Let me know if I misunderstood your question.
from improved-wgan-pytorch.
If i am not wrong, you are talking about Conditional GAN conditioned on class labels. Something like, generate images of flowers and then your code generates them. But, i am looking into slightly different concept of conditional gan. If you take a look into this recent inpainting paper, they condition the gan on the input and not on the classes. That is very typical in inpainting task (slightly different from synthesis problem). In such case some details change as follows:
- We no longer use random noise as input since we are conditioning the input to be specific
- There is an extra loss involved at the generator (Ex: L2 loss) in addition to the already existing WGAN loss
Let me know what you think of it. Thanks a lot for replying instantly though.
from improved-wgan-pytorch.
Yes, if we want to generate a flower which we've already defined a tag (e.g. 1, 2, 3,...) for this flower class, then we put/condition this tag into a noise/input and based on this tag inside the input, the model will know and generate a flower for us instead of image of other classes.
Probably you are looking for something different than the model in this repo.
I don't know if this repo https://github.com/akmtn/pytorch-siggraph2017-inpainting maybe the one you are looking for?
from improved-wgan-pytorch.
Thanks for sharing the repo that performs inpainting. I am more interested in using wgan to do the inpainting task rather than what the paper stated which has a very complex training procedure. What i can do is fork this repo and build it for the inpainting task conditioned on the input incomplete image. Do you have any suggestions?
from improved-wgan-pytorch.
I don' think this current model is not designed to handle such things you wanted since the Generator means to upsample small size of noise to bigger and bigger representation and finally a fake image.
I actually don't know how to make a inpainting task as an input for G in this model.
And even if we are able to create such input layer, we also need to change/re-design middle layers as well.
from improved-wgan-pytorch.
Related Issues (20)
- Why comment aux_errD_fake loss (aux error of fake data during training D)? HOT 3
- RuntimeError: Mismatch in shape: grad_output[0] has a shape of torch.Size([1]) and output[0] has a shape of torch.Size([]) HOT 3
- why doesnt Wasserstein distance in Wgan converge? HOT 1
- Compare to the tensorflow version, this code cost too much time. HOT 2
- Generator loss function HOT 1
- Model Diverge! HOT 2
- cant work :RuntimeError: shape '[32, 3, 96, 96]' is invalid for input of size 580608 HOT 4
- Questions about noise HOT 1
- Backward HOT 4
- One and Mone HOT 4
- Regarding conditioning in the generator HOT 1
- lsun data issue HOT 1
- Increasing dimensionality HOT 3
- Is Wasserstein-distance calculated correctly? HOT 2
- about the size of images HOT 1
- Some question in model.py HOT 2
- batch norm in conditional output branch? HOT 3
- Missing components HOT 1
- A question about loss_G.backward(Mone) HOT 2
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 improved-wgan-pytorch.