Comments (8)
OH, it turned out that scale 0 just worked fine .
And as the scale increases, the differences between output images drop sharply.
The images generated by scale 1 have slightly shift-effect, and the images generated by scale 3 are almost the same.
So, at this rate, there's no need to train over scale 3 at all.
This is pretty amazing .
Thanks for sharing your elegant work.
from singan.
Having the same issue running on Google Colab: seems to stall out at scale 8:[1999/2000]
from singan.
This seems to be a memory problem. When the number of scales is large, there are more model parameters to store.
from singan.
Sorry, I had fat-fingered.(clicked on Close button accidentally.)
I 've checked GPU memory usage while training.
It truly was nearly full loaded when the training stuck.
@tamarott
Do you have any suggestion ?
Is it possible to reduce the batch size or something for avoiding this ?
Or restart training from last checkpoint ?
I read your paper. There's an example of the starry night.
Seems like it goes well on scale 8.
But when I tried Random Samples on scale 8 , it just generated 50 images which are exactly the same as each other.
from singan.
With 16GB of GPU memory, the highest resolution output I have achieved is 667 x 413 from the main training script. Does that seem right? Would changing the aspect ratio let me squeeze more pixels into the model so I can also get more in the final random samples?
from singan.
@phonygene what do you mean by you dont need to train over scale 3? Is it possible to generate arbitrary sized images using just scale 3? How?
Thank you!
from singan.
@rickdotta As I said : In my case, when training scale larger than scale 3 , it only generated identical images, so I tried scale 0 model and found out that it worked fine. I don't understand why it works so differently from the paper, but at least It saves me a lot of time ( troll face ) .
from singan.
@phonygene How do you stop training at a smaller scale?
from singan.
Related Issues (20)
- Does everyone know how to fix this runtime error? HOT 3
- Error: Providing a bool or integral fill value without setting the optional `dtype` or `out` arguments is currently unsupported
- ValueError: the input array must have size 3 along `channel_axis`, got (197, 250) HOT 2
- Why the training always stop at scale 8 ?
- Black Image for fake_sample.png at scale 8 and 9 HOT 2
- How to use SinGAN to perform image translation just as CycleGAN.
- Lack of package versions in requirements.txt file.
- Lack of imsave in random_samples.py
- process of inject scale for image manip (supplemental material figure 3)
- Getting black images as output of harmonization HOT 2
- Can I train model from multiple images?
- mask result image
- version another pytorch intead of 1.4.0
- About Pretrained Model (Harmonize and Super Resolution)
- ValueRrror of SIFID
- No such file or directory: 'TrainedModels/balloons/scale_factor=0.793701,alpha=100/Gs.pth' HOT 2
- SIFID: nan
- draw_concat
- How to input image name
- Python runtime error when training on an image.
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 singan.