Comments (6)
I tried many setups for training, by changing dataset/learning rate/gradient clipping.
The best result is always 0.1~0.3 psnr lower than the original paper.
I forgot the best setup, but as soon as I get the result, I will share it here.
from tensorflow-vdsr.
Same for me... it doesn't reproduce the paper result, psnr are nearly the same with bicubic resize.
from tensorflow-vdsr.
@hetaoaoao There are several reasons for that.
- gradient variation is too high
- training data is too many
- learning rate is too high (this is usually not the case)
Therefore, I recommend you to use a lower gradient clipping norm, or less training examples.
I should have preserved the best setup.. but I finished this code several months ago, somehow the best results are gone. Sorry for any confusions made by me.
I will share the best model and the hyper parameter setup, ASAP.
from tensorflow-vdsr.
@Jongchan Thank you very much.
from tensorflow-vdsr.
@dvornikita @hetaoaoao
Currently, I've managed to achieve the result below. (not fully trained, just a 45-epoch result)
Please allow 2-3 more days for better results, I hope I can achieve somewhat better results and faster training.
Results on Set 5
Scale | Bicubic | VDSR | tf_VDSR |
---|---|---|---|
2x - PSNR/SSIM | 33.66/0.9929 | 37.53/0.9587 | 37.16 |
3x - PSNR/SSIM | 30.39/0.8682 | 33.66/0.9213 | 33.32 |
4x - PSNR/SSIM | 28.42/0.8104 | 31.35/0.8838 | 31.03 |
Results on Set 14
Scale | Bicubic | VDSR | tf_VDSR |
---|---|---|---|
2x - PSNR/SSIM | 30.24/0.8688 | 33.03/0.9124 | 32.81 |
3x - PSNR/SSIM | 27.55/0.7742 | 29.77/0.8314 | 29.62 |
4x - PSNR/SSIM | 26.00/0.7027 | 28.01/0.7674 | 27.83 |
from tensorflow-vdsr.
I'd like to further improve the result, but will close this issue for now.
Link to the actual dataset / latest PSNR result / latest training code is updated.
If I have any further updates, will push to the git.
from tensorflow-vdsr.
Related Issues (20)
- Cannot replicate the layer tensor values HOT 2
- train_data.zip location is offline HOT 1
- About Adjustable Gradient Clipping HOT 1
- Why gradient clipping is removed? HOT 3
- is it required GPU for running? HOT 1
- make_template('shared_model',model) HOT 2
- How many times do you need for training? HOT 5
- Un using Adjustable Gradient Clipping ?
- What does "LR_STEP_SIZE" use for? HOT 1
- Issue in Python 2.7 and Tensorflow
- cannot assign a design for operation 'shared model/conv_20_b' HOT 1
- 时间问题
- the question of time
- The model seems to have a difference from the paper? HOT 2
- Unable to perform normal training HOT 2
- question about network HOT 1
- How do I get an RGB image after testing HOT 1
- Availability of a pre-trained model
- Could you tell me what version of python (tensorflow) you are using?
- Is cpu ok?
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 tensorflow-vdsr.