odeon
odeon copied to clipboard
ODEON is a task-agnostic framework for deep learning applied to remote sensing
#### PITCH: in Odeon, we have created an Env singleton object, configured with a yaml file (env.yaml), instanciated during the bootstrap (see ENV). In this object, we have dependencies to...
Build the CICD pipeline for Odoen based on the python ml skeleton project: https://github.com/samysung/python_ml_project_skeleton Merge it directly on the main branch. **Feature 1A**: Requirement for a modular installation, capable of...
#### Pitch: Odeon must be able to integrate any type of input data (modality agnostic), with potentially different read/write engines. All this while presenting a simple Api that hides the...
Change detection model works well for binary change detection on simple case like building class or tree. However, when we want to apply it to more complexe case like multiclass...
If Input is picked as DataModule for the FIt App, we need to make sure that the Configuration system handles the augmentation instacations with the helper odeon.data.core.transform.build_transform()
updates: - [github.com/psf/black: 24.4.2 → 24.8.0](https://github.com/psf/black/compare/24.4.2...24.8.0) - [github.com/PyCQA/flake8: 7.0.0 → 7.1.1](https://github.com/PyCQA/flake8/compare/7.0.0...7.1.1) - [github.com/pre-commit/mirrors-mypy: v1.10.0 → v1.11.2](https://github.com/pre-commit/mirrors-mypy/compare/v1.10.0...v1.11.2)
updates: - [github.com/pre-commit/pre-commit-hooks: v5.0.0 → v6.0.0](https://github.com/pre-commit/pre-commit-hooks/compare/v5.0.0...v6.0.0) - https://github.com/psf/black → https://github.com/psf/black-pre-commit-mirror - [github.com/psf/black-pre-commit-mirror: 25.1.0 → 25.11.0](https://github.com/psf/black-pre-commit-mirror/compare/25.1.0...25.11.0) - [github.com/PyCQA/flake8: 7.1.2 → 7.3.0](https://github.com/PyCQA/flake8/compare/7.1.2...7.3.0) - [github.com/pre-commit/mirrors-mypy: v1.15.0 → v1.18.2](https://github.com/pre-commit/mirrors-mypy/compare/v1.15.0...v1.18.2) - [github.com/PyCQA/isort: 6.0.0 → 7.0.0](https://github.com/PyCQA/isort/compare/6.0.0...7.0.0)
to handle properly complex and custom data pipeline, the data pipeline needs to be more customizabled, by decoupling loading data, and preprocessing operations, adding dataclass configuration to data module, bring...
### Pitch For SSL experiments, we have implemented specific data loaders for several multimodal datasets in our [code base](https://github.com/IGNF/ssl-models). To limit redundancy, we have designed an [abstract dataset class](https://github.com/IGNF/ssl-models/blob/main/ssl_models/dataset/dataset.py) that...