Comments (3)
Hi! How long time you train this model? Thank you!
from bipnet.
Thank you for your wonderful work!
I'm trying to train with your code, and on the synthetic dataset, BipNet shows excellent results. But on the real burst dataset, It does not give as good results as described in your paper. The loss continues to increase except at the beginning. your code set 1e-5 ~ 1e-6 with CosineAnnealingLR as a default setting. If this learning rate is different from the setting of the experiment in the paper, could you share the training settings for the real burst dataset?
I'm really looking forward to your answer.
Have you any advice to tacle this problem?
from bipnet.
One thing you could try to stabilize the training is to consider a smaller patch size (like 24x24) for training. The aligned L1 loss is computed between the network output (aligned using PWCNet) and ground truth. As you consider a smaller patch size, the minor alignment error between the network output and the ground truth decreases and helps PWCNet in reducing alignment errors. Thus, there is a chance to compute aligned L1 loss with less error.
from bipnet.
Related Issues (20)
- Overfitting on the training set of BurstSR HOT 3
- The problem of test code and PSNR in Grayscale dataset HOT 1
- Color denoising metrics HOT 1
- About testing in low-light enhancement
- BursrSR real dataset training HOT 1
- Loss nan for BurstSR Track 2 training HOT 2
- No training code for denoting
- The Results on Track2 of Burst SR Cannot be Reproduced HOT 1
- About the code for the network
- Question for SR burst training
- Can not download trained model in Color Denoising
- Model class methods need to be overrided caused by Pytorch Lightning HOT 2
- Can't find grayscale_denoising_training.py under Burst de-noising file HOT 1
- There is no training code for burst denoising HOT 1
- About batch size in training HOT 2
- no training code for burst denoising and low light enhancement HOT 1
- The pre-trained model gets no paper points HOT 1
- New Super-Resolution Benchmarks
- The results in Grayscale dataset are 3dB less than the PSNR in paper HOT 2
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 bipnet.