Comments (3)
I presume you are using a multi-gpu setup here.
Yes, this is currently a know issue (bug) with the package. The MinBatchStd layer is not properly optimized to take care of the data-parallel Multi-GPU setup. There is currently no synchronization taking place for the divided minibatch to obtain the proper minibatchstd values back at GPU_1. I am working on a solution which just involves removing the last layer of the discriminator out of the dataParallel block so that everything synchronizes before the last layer's calculations are performed. But this is a temporary solution since, it makes the training way slower and consumes very little of the other parallel GPUs.
For now, you could either ignore the very high loss values produced by only the discriminator [they will go even bigger 😆], because the GAN trains fine. Or, you could run the code on only one gpu.
Please feel free to ask if you have any more questions.
Also, please feel free to suggest if you have a better solution for this problem.
Cheers 🍻!
@akanimax
from pro_gan_pytorch.
@akanimax
Very thanks, it really works. Now I have another problem, the parameter beta of EMA is set as 0 in your code, which means EMA is always closed. Why?
from pro_gan_pytorch.
@akanimax
I'm so sorry. I notice that the zero beta is only for init...
from pro_gan_pytorch.
Related Issues (20)
- Runtime error related to tensor shapes when training ProGAN HOT 2
- If you don't mind, please let me know what environment you are using. HOT 1
- fan-in calculation in _equalized_deconv2d HOT 2
- Memory issues/requirements
- model training plateaus HOT 2
- module must have its parameters and buffers on device cuda:0 (device_ids[0]) but found one of them on device: cpu HOT 1
- no module name pro_gan_pytorch.PRO_GAN HOT 1
- square() not exist? HOT 4
- 256x256 pretrained model HOT 2
- Calculating fan_in for EqualizedConvTranspose2d HOT 2
- Missing LReLU activation after from_rgb conv layers HOT 4
- Output size HOT 6
- Training the model HOT 1
- Training the model
- handling grayscale image
- not "pip install pro-gan-path" but "pip install pro-gan-pth" HOT 1
- Can i use well trained progan generator do gan inversion? HOT 2
- Code profiling
- Could you help upgrade the vulnerble dependency in pro-gan-pth HOT 2
- pretained model HOT 13
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 pro_gan_pytorch.