Comments (2)
Hi @davidhalladay, thank you very much for your help!
I downloaded again the coco dataset and run the scripts.
I got FID=38.58
... up to some randomness it should be ok, right?
from frido.
Hello helia95,
Thanks for using our code! You used the commands correctly.
Yet, I tested the evaluation code on aother server again and got the correct FID results (37.41) today, so I'm not sure which part might cause the error.
Could you check that the number of generated results is 2048? Since the number of results may largely effects the FID scores, I'm concerned that the evaluation could be terminated, and not all images were generated.
As for the issue of 2,048 val images, thanks for pointing it out (same issue in here.). I have added the setting for 2048 val image ids in the new config and have it updated. But, I think it should not effect the score that much. For qualitative results, I provide some randomly selected results below for reference. Also, you can turn on classifier-free guidance to further improve the generated quality, please refer to the bash script of text-to-image evaluation.
Thanks!
from frido.
Related Issues (7)
- when the training codes can be released?
- Layout2Image: Do you train on the deprecated coco-stuff 2017 segmentation challenge or the full coco-stuff 2017?
- Sample times for each image? HOT 9
- Model size HOT 2
- Thanks for your great work, can you release pretrained models of layout-to-image generation on coco-stuff?
- RuntimeError: each element in list of batch should be of equal size
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 frido.