Comments (1)
As of today, Albumentations has too many limitations (for our purpose), such as:
- Most of the transformations can only be done on 3 channel images. Our system is generic anough so someone would be able to use it with >3 channels input images. An example of this limitation is provided in the code here
- Some transformations assume that input images are uint8. Since we do not want to limit the use of GDL to uint8 images, I'm not sure we should use libraries that makes that assumptions.
Albumentations is not quite suited for our purposes. We'll reconsider the use of this library (or another one) to manage data augmentation later.
In the meantime, we'll still expose our data augmentation operations in the configuration file.
from geo-deep-learning.
Related Issues (20)
- multiclass loss computation error for validation and test
- Additional geometry checks needed
- Test don't cover all the functions in test file
- To many patches after tiling (for flood modelling interest) HOT 1
- AOI covering test
- Add Vision Transformer Model
- Add Centerline loss
- Not supporting multilayer gpkg annotation
- Minor fixes for smoothening with hann windows
- Generate idx for train/val/test dataloaders from raster mask values HOT 1
- Empty Dataloader HOT 2
- Dataset split. HOT 1
- inference: add "total=" arg to tqdm to provide ETA during inference
- get_key_def(): unnecessary logging polutes stderr
- add PR template HOT 2
- Create Github issue template
- Resolve naming convention for duplicate image filename
- Add configurable parent directory for patches
- BUG: GDL cannot write TIFFs larger than 4 GB
- BUG: broken CI pipeline 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 geo-deep-learning.