Comments (11)
training step runs #200 epochs by default.
from waifu2x.
Another question about training: does the batch_size
make any quality difference or is it just for performance tuning?
from waifu2x.
In waifu2x, computing performance mostly not influenced by batch_size (but slow performance when batch_size=1).
I recommend small batch_size (2~4).
small batch_size: low memory usage. fast convergence. reducing over tting.
NOTICE: waifu2x is using Adam for CNN training (http://arxiv.org/abs/1412.6980)
from waifu2x.
I have another question: how long did the entire training process take for your training set?
from waifu2x.
2x scaling model: 16 hours
Noise reduction model: 28 hours * 2
Total: around 72 hours
(on GTX760, 3000 images)
from waifu2x.
The facts brought up here (how long training takes, batch size recommendation, epochs to training end) should be added to the documentation - they would be EXTREMELY useful to someone like me trying to train their own model.
from waifu2x.
Could you please let me know how many iterations did you train it for? Also did you use all the current default settings when training your anime model?
from waifu2x.
See https://github.com/nagadomi/waifu2x/blob/master/train.sh
The default setting is defined at https://github.com/nagadomi/waifu2x/blob/master/lib/settings.lua
I was used 3000 images for training.
And I'm currently running the traning script for the next version using dev branch code and 6000 images.
from waifu2x.
Thanks! Could you share what the next version is and what the differences are?
from waifu2x.
I released new version yesterday.
Summary of difference in training script:
- Add data compression method for on-memory image (reducing memory usage for dataset)
- Change loss function (MSE to Customized Huber Loss)
- Improve some image processing functions
- Add some data augmentation methods
- Tuning default parameters
- Improve code readability
- Improve training time (4x~ faster)
Sorry, my english skill is very poor. Please refer the code for more details.
from waifu2x.
I would like to ask you a hypothetical question. If I have only one specific type of image I want to scale up, would it be possible to train the algorithm only on one perfect image with maximum resolution?
from waifu2x.
Related Issues (20)
- Image getting "overexposed" if it has transparent corners HOT 2
- Web in Galician HOT 1
- Jpeg noise removal not working HOT 7
- I want to use the version before the update HOT 3
- What are the best settings to upscale a 480p cartoon show to 1080p?
- Add homebrew support HOT 1
- Filename gets truncated if it has a dot in it HOT 1
- Different on Noise Reduction in cloud version after update 02.02 HOT 2
- [unlimited:waifu2x] Error: TypeError: Cannot read properties of null (reading 'run') HOT 9
- Feature request HOT 1
- Use waifu2x Docker image without Nvidia HOT 18
- Will the Waifu2x browser plugin be created?
- Can't query my GPU ID correctly HOT 6
- use nvidia gpu on https://unlimited.waifu2x.net/ on win 11 HOT 2
- Program closes after I start upscaling HOT 2
- Can I get portable version of project? HOT 1
- Persist 'optimize looped video'-option
- May I ask the author, can this model improve the resolution of real person images? HOT 2
- unlimited.waifu2x : using 4x upscale + TTA enabled (2 or 4) results in "Error: 75952160" HOT 1
- Waifu2x (aumenta resolución de imagen)
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 waifu2x.