Comments (6)
@xuyu666 您好,
除了减小batch size还可以尝试减少channel,参考train.py里的args.G_kwargs.synthesis_kwargs.channel_base和channel_max
from dfmgan.
谢谢你的回复,我尝试了你说的方法,修改成功了。但是运行的时候一直不动了(此时显存貌似没调用,但默认batch16时直接显存不足),具体如下:
from dfmgan.
看这张图卡住的位置程序应该在算FID,默认要生成50k张图片,本身时间就比较久(几分钟以上)。这里可以尝试--metrics fid5k_full
减少生成图片数量到5k张确认一下程序是否在正常运行
如果还是卡住,可以检查一下两个pytorch插件有没有配置成功
Setting up PyTorch plugin "bias_act_plugin"... Done.
Setting up PyTorch plugin "upfirdn2d_plugin"... Done.
from dfmgan.
好的谢谢,目前去掉指标测试后运行成功。另外想了解下您代码里的rank参数默认为0,能否对其修改。单卡gpu设置为1时,貌似存在一个冲突,具体如图所示。同时我看您论文中有提到supplementary material,能不能发我一份看看哈哈哈(ps: 邮箱[email protected])
from dfmgan.
rank这部分是StyleGAN-ADA的代码,我没有尝试过修改
补充材料在arxiv版本里有
from dfmgan.
有看到,谢谢hahah~
from dfmgan.
Related Issues (20)
- 使用图片label作为生成条件的疑惑 HOT 2
- RuntimeError: DataLoader worker (pid(s) 68788) exited unexpectedly
- it doesn't make any pkls/ng.pkl HOT 1
- SDGAN, Defect-GAN HOT 1
- Supplementary material HOT 2
- RuntimeError: Ninja is required to load C++ extensions HOT 4
- “Discriminator.b16.conv1.weight”出现异常 HOT 1
- res_block_match_dis error HOT 5
- 预训练时报错 HOT 4
- hazelnut_good.pkl和hazelnut_hole.pkl是如何训练生成的 HOT 3
- 环境问题 HOT 2
- hazelnut hole defect train HOT 5
- 生成图像效果问题 HOT 1
- dataset_tool.py /gray scale image HOT 1
- 训练第二阶段显存不够 HOT 2
- 预训练时间 HOT 5
- Pytorch version Compatibility HOT 2
- Training MVTec Wood datasets & Different inference results HOT 3
- Training Issue with Transistor Class HOT 10
- 生成图像的mask可以自己指定吗,即使用自己的mask来生成图像 HOT 1
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 dfmgan.