Comments (1)
Hi @Stephenlove,
Thank you so much for being so interested in the repo! When I started to implement, I used v2.0 of the paper. The results are different since the hyperparameter I used wasn't too many comparing to the original implementation. Also, there is limited computational power&GPU to train the model, and I have ongoing projects that's why I couldn't further develop performance. Therefore, the FID score is different from the reported results! However, qualitative results are reasonable, and it shows that it is open to developing the performance. I hope this could answer your question!
from transgan.
Related Issues (15)
- Maybe you can tell how to train it HOT 1
- Hi, I found that hinge loss doesn't work well, is that right? HOT 2
- GPU memory, Modifying batch size HOT 10
- Is there a pre-trained model? HOT 3
- Can you resume training at breakpoints? HOT 2
- sir,I have a question about the DiffAug, the paper said they used the Data Augmentation to get excellent improvement. It is about translation, cutout, color. So, in your code, did you use the DiffAug? HOT 1
- Hello, I can't download the file fid_stats_cifar10_train.npz that you provided in readme! HOT 1
- when i train my own data , i meet FID score :nan ,what's wrong with it HOT 2
- Could you give me a pretrained model, please? HOT 1
- FID score: nan HOT 1
- Create your own FID stats file HOT 2
- How do you test on your own dataset with the checkpoint.pth generated?
- question about argumentation
- Questions about multi-GPU training
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 transgan.