Comments (13)
Currently I am trying to improve the training of SRGAN to make it more stable
from srgan-pytorch.
From the current point of view, the training of GAN still has the problem of "model collapse", and it may be necessary to find the best model from the training node of GAN
from srgan-pytorch.
You need to wait patiently for the training results and choose the best one.
from srgan-pytorch.
I think he meant wait till the end of the training process. Surprisingly, your model can perform badly during a lot of iterations and then, suddenly, you will see the D(SR) increase and the D(HR) decrease, which is what you want. You just need to be patient due to the instability of GAN training :(
from srgan-pytorch.
For example these methods
WassersteinGAN
WassersteinGAN_GP
from srgan-pytorch.
This is also the case for me during training, usually a common problem when training original GANs.
from srgan-pytorch.
Should I still expect some good results ?
Or do I need to investigate on how to fix it ?
from srgan-pytorch.
Thank you very much, I now better understand GANs evaluation.
Beautiful work on this repo
from srgan-pytorch.
Thank you.
from srgan-pytorch.
Are you saying that you are learning several times to find the optimal model or that you are learning to the end and finding the optimal model among them?
from srgan-pytorch.
Ok thx a lot
from srgan-pytorch.
Currently I am trying to improve the training of SRGAN to make it more stable
How many iterations do you use to train your model ?
I would be interested in knowing what approaches you are going to use to make the training more stable as I am really interested in the subject
from srgan-pytorch.
I will not update on this library though, as this library is the closest implementation to the original paper
from srgan-pytorch.
Related Issues (20)
- Torch not compiled with CUDA enabled HOT 1
- TypeError: 'type' object is not subscriptable HOT 3
- TypeError: unsupported operand type(s) for |: 'torch._C._TensorMeta' and 'type' HOT 6
- Resnet Models num_blocks HOT 1
- How do you test the SRResNet Models? HOT 1
- TypeError: preprocess_one_image() missing 2 required positional arguments: 'half' and 'device' HOT 1
- model_weights_path HOT 1
- TypeError: discriminator_for_vgg() got an unexpected keyword argument 'in_channels' HOT 4
- Traceback (most recent call last): File "F:\SRGAN-PyTorch-main\test.py", line 190, in <module> main() File "F:\SRGAN-PyTorch-main\test.py", line 169, in main config["ONLY_TEST_Y_CHANNEL"], KeyError: 'ONLY_TEST_Y_CHANNEL' HOT 1
- About Training with SRGAN HOT 1
- about upscale==3 HOT 5
- train_gan.py : Model weight file not found, state_dict Missing key(s), Unexpected key(s) HOT 1
- Train Code HOT 1
- Unable to reproduce the result of SRGAN_x4-SRGAN_ImageNet.pth.tar HOT 1
- Test out of memory HOT 1
- Issues running the test.py HOT 4
- The dataset have changed? HOT 1
- AssertionError: Supplied images have different sizes torch.Size([1, 3, 2048, 2048]) and torch.Size([1, 3, 128, 128])
- There is no scheduler at saving checkpoint
- test.py doesnt save results 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 srgan-pytorch.