Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

Sign up
Appearance settings

a python image data augmentation library for deep learning

Notifications You must be signed in to change notification settings

Hsuxu/Image-preprocessing

Folders and files

NameName
Last commit message
Last commit date

Latest commit

History

13 Commits

Repository files navigation

Image-preprocessing

This a python image data augmentation library based on opencv and numpy for deep learning for persenal usage. This library is compatible with Datagenertor in Keras and Dataset in PyTorch Any question please

Components

  • Remove mean
  • Fix normalization with mean=[0.48462227599918, 0.45624044862054, 0.40588363755159], std=[0.22889466674951, 0.22446679341259, 0.22495548344775] which is computed from ImageNet.
  • Instance normalization(Adaptive normalization
  • Adjust contrast
  • Random flip up-down left-right
  • Crop image with a given size
  • Image edge padding

Requirements

pip install numpy
pip install opencv-python

Installation:

python setup.py install

About

a python image data augmentation library for deep learning

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

AltStyle によって変換されたページ (->オリジナル) /