Comments (1)
lavi135246
commented on September 26, 2024
Hi @Sun-Fan ,
If you read the readme carefully, you may see that the result is shown in the figure at the end of the readme. Since Pytorch somehow needs more GPU resources than tensorflow in this case, I could only slice the original input images into small pieces before feeding them into the model. I am quite sure that the model will perform well if it takes in whole images.
Also, I have provided a trained model for sony dataset. You may download it and try by yourself.
from pytorch-learning-to-see-in-the-dark.
Related Issues (17)
- Why permute (0,3,1,2) is required? HOT 2
- Cant make it work on Cuda [windows] HOT 2
- Maybe There is a bug in train.py, when flip the image HOT 1
- cuda memory insufficient HOT 1
- about train_sony code HOT 2
- Test HOT 6
- Where is the slice operation in test code? HOT 1
- Question about initializing the weights
- 模型输出的图片好像没有颜色信息
- Does the function _initialize_weights() necessary? HOT 1
- about the loss function HOT 1
- im = raw.postprocess HOT 1
- scale_full HOT 2
- gt_full = np.expand_dims(np.float32(im/65535.0),axis = 0) HOT 4
- Training time? HOT 1
- Considering your failure case 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 pytorch-learning-to-see-in-the-dark.