Comments (3)
is there specific recommendations about lambda_ds in general?
should it be equal to the domain count (minus one?)?
training 7 domains with lambda_ds=2 results in rather subtle variety
from stargan-v2.
@eps696
I have same question. I tested only 3 domain with my own dataset, and it preserves the identity in certain degree.
from stargan-v2.
@iPsych i have trained ~dozen models with 7-8 domains on two configs: img_size 512 batch 1
and img_size 256 batch 3
(these are maximum batchcounts for original code on 11gb 1080ti).
i got satisfactory results (worse than original model though) with lambda_ds
, lambda_cyc
& lambda_sty
all equal 3. increasing lambda_ds indeed leads to losing identity (increasing lambda_cyc
seems to get it back).
two more observations:
- lower batch counts definitely lead to worse quality; the experiments with
img_size 512 batch 1
were not quite successful. as the authors said, the result is not guaranteed with batch count < 8. - after adding
del x_fake2, y_org, y_trg, s_trg2, s_trg, s_pred, out
before this line, i was able to start training withimg_size 256 batch 4
on 11gb gpu (no results from that yet).
from stargan-v2.
Related Issues (20)
- 对于数据集,我该如何下载,我在国内,实在不懂,麻烦指点一下 HOT 9
- How to train stargan-v2 on my own dataset? HOT 2
- Question about the domain information of y_org & y_trg
- Changing initial latent code z for translation between domains
- The reason for not updating the style encoder for g_loss on reference images
- RuntimeError: Error(s) in loading state_dict for DataParallel
- The author's checkpoint is whether suitable for style transformer on market1501 HOT 1
- Error in transforming custom image script, and error in running the program script (to generate images and videos) HOT 4
- 😵 Uh oh! This model can't be run on Replicate because it was built with a version of Cog that is no longer supported.
- How to get a pre-trained model with the ckpt file? HOT 1
- How to change device of gpu
- Generated image didn't change when performing the task of face to anime.
- How to modify the code if use torch>1.4
- AFHQ Alignment
- why we need to label data from famale and male?
- Train own dataset
- need help
- License
- only noise output when --mode sample
- AFHQ link is disabled HOT 2
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 stargan-v2.