https://github.com/hereariim/deep-image-processing
Hands on for academic lecture
https://github.com/hereariim/deep-image-processing
Last synced: 10 months ago
JSON representation
Hands on for academic lecture
- Host: GitHub
- URL: https://github.com/hereariim/deep-image-processing
- Owner: hereariim
- Created: 2025-01-13T13:27:45.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2025-02-23T16:13:24.000Z (over 1 year ago)
- Last Synced: 2025-08-15T23:37:43.464Z (10 months ago)
- Language: Jupyter Notebook
- Size: 76.9 MB
- Stars: 2
- Watchers: 1
- Forks: 2
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Deep-image-processing
Hands on for academic lecture
This lecture focus on the use of codes to run and assess deep model. We are interested on image classification and image segmentation. In view of the range of existing models, we use a classical architecture: CNN and UNet.
## Image classification
## Image segmentation
Data :
- [Nuclei data](https://drive.google.com/file/d/1ZNoqmFJVK-1n9CtgfNI1B2UrKs_5aZRA/view?usp=drive_link)
- [BCCD](https://www.kaggle.com/datasets/jeetblahiri/bccd-dataset-with-mask?resource=download)
## Object detection and Foundation model
Data :
- [Apple](https://uabox.univ-angers.fr/s/XWRYs3j7Aw8T9f7/download/Apple.zip)
Liens utiles :
- [DINO](https://deepdataspace.com/playground/grounding_dino)
- [Yolov11](https://docs.ultralytics.com/fr/models/yolo11/)
- [Hyperparamètres](https://docs.ultralytics.com/modes/train/#train-settings)
- [Prediction](https://docs.ultralytics.com/modes/predict/#key-features-of-predict-mode)
### Deploying model with Napari for public usage
Nous allons travailler sur Napari. Si vous êtes muni de votre PC portable, vous devez installer anaconda puis napari (consignes d'installation dans l'exercice 1).
### Conclusion