Comments (5)
I don't have a clue from your message but my guess is lack of shared memory.
Could you try with smaller val_batch_size
?
--val_batch_size 4
Or, you can try other ways to save the video, for example, imageio.mimsave()
from stargan-v2.
@edmar I had faced the same issue earlier with a 16GB RAM machine. The process is killed because video creation is fairly memory intensive. If you just want to let the model run and see how images are transformed (without creating a video), simply comment out lines 187 to 189 in /core/solver.py
from stargan-v2.
I upgrade the machine to check if it was a memory problem. Now I am running on:
total used free shared buff/cache available
Mem: 62G 340M 60G 860K 881M 61G
Swap: 0B 0B 0B
But it didn't work. Using the --val_batch_size 4 now I can see the video being generated.
However, it only generates the female video. Is this the correct behavior?
from stargan-v2.
I had the same error with the "Killed" as you did. I have a 64 GB Ubuntu Linux server and memory did not appear to be the problem. When I set val_batch_size to 4, 8 or 16, they all worked. At 4, I also only got 4 female faces. At 8, I got 5 and 3 female/male faces. 16 gives 6 and 5. So just specifying the option fixes the problem for me.
from stargan-v2.
Bump. I have the same problem as edmar except that I don't get killed. But I don't get the video anyways.
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.