This project presents a deep-learning pipeline for medical object detection and classification. This project is part of the Kaggle competition VinBigData Chest X-ray Abnormalities Detection.
The report is available at Medium: Article
The following code folders are included in this project:
- 'data' contains data to be used for training
- 'results' contains the results of the experiments
- 'models' contains the models used for training
- 'utils' contains the utility (WBF, merging algorithms, etc.)
Models used during the project and available in code:
- YOLOV5
- YOLOv8
- EfficientNet-B7
- EfficientNet-B6
- EfficientNet-B5
- EfficientNet-B4
- EfficientNet-B3
- Resnet-18
- Resnet-50
- Resnet-101
- Resnet-152
- DenseNet-121
- DenseNet-169
- DenseNet-201