Comments (2)
Hi,
We use 2 NVIDIA Tesla V100 GPUs to train the model. With your GPU of 24GB memory, I would suggest either reduce the batch size to 8, Or keep the batch size 16, but change n_feat=32 in the model file (This will make the model lighter but with a minor compromise on accuracy
MIRNet/networks/MIRNet_model.py
Line 347 in a668d27
Since the SIDD training images are of very high resolution, you can first crop patches offline (from the full resolution images) and then train the model on these patches. In our case, we cropped 350 patches of size 256x256 from each image (totalling 350*320 patches).
Regarding the training code, we are aiming to release it in two weeks' time.
from mirnet.
Thank you so much for your reply! I will retry it!
from mirnet.
Related Issues (20)
- There is a question that the data processing of super-resolution and the data processing of Image denoising? HOT 2
- training.yml for LOL enhancement HOT 2
- About SR premodel
- Training Dataset link for Image Enhancement? HOT 2
- Questions on Enhancement.pth HOT 2
- Parameters and FLOPs HOT 1
- Training Details on RealSR Dataset HOT 1
- Which SSIM implementation? HOT 1
- Train HOT 3
- doubt regarding training on denoising dataset
- Can't evaluate - ModuleNotFoundError
- Implementing SKFF with Tensorflow
- NameError: name 'warmup' is not defined HOT 5
- torch.clamp
- Some questions about your code HOT 1
- Log Files from Training HOT 1
- Question in MIRNet_model.py
- SIDD dataset is not avaiable HOT 1
- A lightweight, fast and extended version of MIRNet is accepted in TPAMI HOT 2
- Questions regarding the SIDD dataset split 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 mirnet.