Comments (4)
I use multi spectral images: RGB, IRA, IRB, IRC, ... So I stack them up to something like 6 channels image.
I still want to do some brightness and color augmentation. So I use PerChannel
to select and apply color jittering to the "color" image in my stack, and apply Brightness and contrast to the other channels in my image stack. At least that how I hope it should work.
Otherwise, I need to do a separate augmentation pipeline for each type of image independently and then stack them before feeding it to the model ? How would you do that with mmpretrain
for example ?
from albumentations.
I it an experimental feature and just adding it to __all__
is not enough.
- Some transforms like
ColorJitter
could not be applied to one channel, but require 3 channel images. => It should be a Separate Transform, saySubsetChannels
- In the existing implementation, there is no guarantee that it will be the same transform, applied to different channels as many transforms sample random parameters and different channels would get different values.
We could address both issues and make things work as expected. (It is not just adding to __all__
).
But, for use to better understand how to do it better, could you please share what problem do you face that requires transform being applied to a subset?
from albumentations.
I see. Yep, for stacking images made sense. I did something similar working with satellite images before Albumentations.
We will add the desired functionality. Hopefully in the next couple weeks, before the next release.
from albumentations.
Added in #1690
But it is called: SelectiveChannelTransform
from albumentations.
Related Issues (20)
- [Performance] Vecorize bounding boxes and keypoints
- [Feature request] Add apply_to_batch
- The bbox obtained with HorizontalFlip has a pixel difference HOT 2
- Augmentation outputs Incorrect Bounding Boxes Values HOT 4
- module 'albumentations' has no attribute 'IAASharpen’ HOT 1
- [Tech debt] Enable typing checks with "numpy.typing.mypy_plugin"
- [Bug] RandomShadow HOT 1
- How It's works "Normalize" function HOT 2
- [Feature Request] Add multichannel support to RandomShadow
- [Tech debt] Remove scikit-learn as depencency
- check_for_updates error HOT 1
- UserWarning: Got proce ssor for bboxes, but no transform to process it HOT 3
- Error "Key image is not in available keys" for empty transform HOT 2
- Min-max normalization resulting in nan values on all-zero arrays HOT 2
- [Performance] Move addition to albucore
- [Performance] Move add + multiply to albucore
- [Performance] Move power to albucore
- [Performance] Move normalize to albiucore
- [Performance] Move add_weighted to albucore
- Check_for_updates TimeoutError: The read operation timed out
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 albumentations.