Comments (3)
Hello! For the training step, the input of the network is the image patch (e.g., 112x112 pixels patch for LIVE dataset). For the training details, you can refer to the describes of the original paper "G. Patch-Based Training", "In the DIQA framework, the sizes of input images must be fixed to train the model on a GPU. Therefore, to train the DIQA using images of various sizes, such as in the LIVE IQA database [5], each input image should be divided into multiple patches of the same size. Here, the step of the sliding window is determined by the patch size and the number of ignored pixels around the borders to avoid overlapping regions when the perceptual error map is reconstructed."
from diqa.
Can we resize the input image using transform function? or we must divide it into patches
from diqa.
Can we resize the input image using transform function? or we must divide it into patches
I might also change the input size of the model if I am using a dataset that input size is not that large and the same. In this case I don't need patch-based training. Is that right?
from diqa.
Related Issues (5)
- question HOT 1
- some error HOT 1
- about loss HOT 10
- May be an error in your code of IQADataset.py HOT 1
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 diqa.