Comments (2)
Hi Touqueer
Due to the GAN based training, the loss functions are expected to behave like this. The best way to check if training works is to look at the results.
Regarding the results, I would expect them to be blurrier than bicubic. This is because, counterintuitively, bicubic downscaling makes the images look "sharper" than images of the same size that were not bicubicly downscaled. Consider for example an image where the lines typically have a width of n pixels. If you downscale this image, then the width of these lines will decrease. Therefore, the image appears sharper in comparison to a cropped version of the original image.
In order to see if the model works, you would have to compare the output with a cropped input image and see if it looks more "similar" than the bicubic image. In your case this similarity might be hard to determine, because the output and bicubic images are quite similar already.
Finally, you could of course just train a super-resolution model with the generated training pairs and see if the model works better for upsampling. Of course the test images should not be bicubicly downscaled images, but images from the same source as the HR training images.
from real-world-sr.
Further to my concern above, I trained DSGAN on Flickr2K dataset in unsupervised setting without adding any degradation. Used 2600 images for training and 50 for testing, the loss curves for training and validation are available on the following link:
https://drive.google.com/open?id=1tqIYxIAFSK87kdRPIyk_g-dlSL3314NH
We can see the generator's texture and perceptual losses are moving in the wrong direction, is it an expected behavior in DSGAN? Also, after training, generating the LR frames for the training data results into images which are blurrier than bicubic -- some samples are available on the link above. Looking forward to hear back from you.
Touqeer
from real-world-sr.
Related Issues (20)
- LR image generation HOT 2
- issue in DSGAN part about the UNsupervied training HOT 2
- didn't match because some of the arguments have invalid types: (list, keepdim=bool)
- _pickle.PicklingError: Can't pickle <function <lambda> at 0x7f308810e2f0>: attribute lookup <lambda> on __main__ failed
- WIll I need to retrain DSGAN for 2x SR? HOT 1
- There is no if __name__ == '__main__': in train.py
- RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.FloatTensor [1, 256, 1, 1]] is at version 2; expected version 1 instead. Hint: the backtrace further above shows the operation that failed to compute its gradient. The variable in question was changed in there or anywhere later. Good luck! HOT 15
- where are the options for testing? HOT 1
- ModuleNotFoundError: No module named 'PerceptualSimilarity' HOT 1
- Where is the source images Z for Discriminator?
- As for PerceptualSimilarity
- Pre-trained Models
- Files for DSGAN SDSR pretrained model broken HOT 1
- cannot import name 'models' from 'PerceptualSimilarity'
- no attribute PerceptualLoss HOT 8
- Trouble training ESRGAN with jpeg artifact images. HOT 2
- About test.yml HOT 5
- Why the dsgan's pretrained models can't uncompress? HOT 3
- Could I use the dsgan with my own image? HOT 4
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 real-world-sr.