Comments (1)
general image SR: about 5 days for training on 3 RTX 2080 Ti, about 18 mins for testing on 1 RTX 2080 Ti for DIV2K validation set, 27M parameters.
face image SR: about 8 days for training, about 37 mins for testing on 1 RTX 2080 Ti for CelebA first 5000 testing images, 23.2M parameters.
image rescaling: about 3.5 days for training on 2 RTX 2080 Ti, about 8 mins for testing on 1 RTX 2080 Ti for DIV2K validation set, 4.4M parameters.
As for the FLOPS, sorry that I don't have time to calculate them recently. You can download the code and calculate the FLOPs yourself. Share it with us if you do it. Thank you!
By the way, if you want to do similar experiments, my advice is that you first set up a tiny baseline model with less flow layers for each level. It would be much faster.
from hcflow.
Related Issues (13)
- How to make an invertible mapping between two variables whose dimensions are different ?
- How to build an invertible mapping between two variables whose dimensions are different ?
- RuntimeError: The size of tensor a (20) must match the size of tensor b (40) at non-singleton dimension 3
- Why NLL is negative during the training?
- New Super-Resolution Benchmarks
- NAN
- Testing without GT HOT 4
- NaN when training HOT 5
- Does the resolution of LQ images will affect the quality of results? I use the 256x256 LQ images for inference and the results are bad HOT 4
- environment HOT 2
- The code implementation and the paper description seem different HOT 2
- Code versions of BRISQUE and NIQE used in paper HOT 1
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 hcflow.