Skip to content

Cause the original CEIQ code is written in MATLAB, it is difficult to integrate the model into python codes. This CEIQ model is trained on kadid10k dataset, which contains only 220 images vs 1500+ used in the original model. Therefore, the results may different and not so accurately compared to the original model.

Notifications You must be signed in to change notification settings

nlgkhoi/ceiq-python

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

ceiq-python

This is a Python implementation of CEIQ

Requirements

pip install -r requirements.txt

Import and go

The model accepts two kinds of input type:

  • Option 0: Predicting score with inputs are paths to images.
  • Option 1: Predicting score with inputs are RGB matrix reprentation of images.
model = CEIQ()
results0 = model.predict(['test_imgs/1.png', 'test_imgs/2.png'], 0) # 'option' is set to 0 to indicate prediction from paths

img1 = cv2.imread('test_imgs/1.png')
img2 = cv2.imread('test_imgs/2.png')
results1 = model.predict([img1, img2], 1) # 'option' is set to 1 to indicate prediction from BGR matrix representations of images

print(results0, results1) # the two outputs are supposed to be the same

About

Cause the original CEIQ code is written in MATLAB, it is difficult to integrate the model into python codes. This CEIQ model is trained on kadid10k dataset, which contains only 220 images vs 1500+ used in the original model. Therefore, the results may different and not so accurately compared to the original model.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages