Comments (7)
@iboates you are back! any interesting training results? :)
Those are the vital signs of the training, the numbers that the network is forced to try to minimize.
G: generator loss
D: discriminator loss
GP: gradient penalty loss
PL: path length regularization loss
G and D are fighting each other, and ideally stay flat. When D hits 0 consistently, training is usually done, and the best generator is a few saved models behind. GP should be 0 for stability. PL will occasionally spike as G learns something new, but should ideally be pushed back close to 0.
from stylegan2-pytorch.
Thanks for the info.
The results so far have been disappointing unfortunately. I have been trying to train it on images of maps coming from openstreetmap.
It was making good progress, but after about 70k iterations the model collapsed and began outputting random smears of colour. I was thinking that maybe it had to do with the fact that the data pool was pretty small, and what images I did have had quite a bit of variety.
So I have come up with a way to get much more data, and isolated the maps so that they are always featuring villages or small towns. I'm training again with about 3k of these images, but I can generate many many more. But right now I think I am hitting the upper end of Google Colab, it takes about 7 hours to do 10k iterations, and that is when the checkpoint is made. Since Colab disconnects after 10 hours, I can't really squeeze more data in. I think I have to buy some cloud processing time or something.
This was about as good as it got before collapsing:
from stylegan2-pytorch.
@iboates ahh 3k training set is nothing! you need up to 10k or more!
from stylegan2-pytorch.
Thanks for the clarification. We're a bit off-topic from the original question, but how many faces did you train it on for thispersondoesnotexist.com? And do all the images have to be the same size or can they just be of similar size & resolution to depict what they are showing?
from stylegan2-pytorch.
@iboates to get to that level of quality, I would recommend the official repository, as it is more optimized. That model was trained on 70k high quality images by Nvidia
from stylegan2-pytorch.
Do all the images need to be the exact same size?
from stylegan2-pytorch.
@iboates ideally yes!
from stylegan2-pytorch.
Related Issues (20)
- What do the G, D, GP, and SS numbers mean? HOT 1
- I get a "DefaultCPUAllocation error: not enough memory" error
- Parameters for generating faces HOT 1
- Performance on MNIST
- Out of memory after exactly 5024 iterations? HOT 1
- Web application for generating content while reloading.
- Tesla V100 GPU - 2600 Image - Too Slow Training HOT 1
- Uneven GPU utilization.
- Trainning on images with one (single) channel HOT 1
- Bug: random_hflip function HOT 1
- where can i download train data?
- Bug: gradient_accumulate_contexts function HOT 1
- Generate full resolution images 1024x1024 HOT 1
- generate all seeds of latent space
- ability to calculate Perpectual Path Length (PPL)? HOT 1
- Save Interval Flag
- /torch_utils/custom_ops.py - _find_compiler_bindir: incorrect Visual Studio Path
- Inconsistent evaluation of self.av HOT 2
- How to Train on a Single Image
- Examples on save_every and evaluate_every in README section needed.
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 stylegan2-pytorch.