Comments (5)
Yes indeed! It's one of the GANs I'm considering to add in the future, will keep this issue open and update it when it's done!
from mimicry.
Hi everyone, I've implemented SAGAN (https://github.com/kwotsin/mimicry/blob/master/torch_mimicry/nets/sagan/sagan_128.py) but it seems since the original paper only trained on imagenet 128x128 that requires about 2 months to train using 1 GPU (1M iterations), I might not have the resources to reasonably train it on time. However, I provided the implementation in the master branch which you can install to check it out, and if you have the resources to train the model, please feel free to share the checkpoint weights!
I also included an extra 32x32 version of SAGAN which I think is easier to train, although of course the implementation is "unofficial" since the placement of the self-attention block may not be optimal, and there's no reference implementation.
Will keep this issue closed for now but will update/reopen if there are any changes. Thanks everyone!
from mimicry.
Also Biggan if possible?
from mimicry.
@zhangmozhe in the case of BigGAN there's an "official unofficial" pytorch implementation by the authors written for reproducing their results
from mimicry.
@zhangmozhe Thanks for the suggestion! I'll look into BigGAN as well although I might not have enough resources to train it using the hyperparameters suggested (will check again)
from mimicry.
Related Issues (20)
- Cannot import sagan when I use pip install. Please fix. HOT 1
- Some cons when using metric... HOT 3
- Evaluation settings question HOT 4
- Pretrained Discriminators HOT 3
- Difference of spectral norm conv2d in Dblock/DBlockOptimized
- Evaluation on the test set HOT 1
- How to judge the training process is correct HOT 1
- The gap of FID on LSUN dataset. HOT 1
- Could you add the SAGAN for 256x256 size image? HOT 2
- Could you add the support for torch >= 1.8? HOT 1
- LSUN bedroom 128x128 HOT 1
- bugs in README.md and Documentation about evaluate HOT 2
- dtype bugs on windows10 HOT 1
- How to calculate the FID IS after the experiments? HOT 4
- fid_score() got an unexpected keyword argument 'dataset_name' HOT 1
- ImportError: cannot import name 'PY3' from 'torch._six' HOT 1
- size mismatch for block4.c2.weight
- In which file should I modify the structure of a specific model?
- [CelebA]RuntimeError: The daily quota of the file img_align_celeba.zip is exceeded and it can't be downloaded. This is a limitation of Google Drive and can only be overcome by trying again later. HOT 1
- ImageNet token is empty. Please obtain permission token from the official website.
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 mimicry.