rsna-pneumonia-yolov8s

---

          title: RSNA Pneumonia Detection YOLOv8s
          tags:
          - object-detection
          - medical
          - pneumonia
          - yolov8
          - pytorch
          library_name: ultralytics
          ---

          # RSNA Pneumonia Detection Model (YOLOv8s)

          This repository contains a YOLOv8s (small) model trained for detecting Pneumonia (Lung Opacity) from chest X-ray images, based on the RSNA Pneumonia Detection Challenge dataset.

          ## Model Details
          - **Architecture**: YOLOv8s (from Ultralytics)
          - **Task**: Object Detection
          - **Classes**: `pneumonia` (1 class)
          - **Input Image Size**: 640x640
          - **Training Data**: Subset of RSNA dataset with bounding box annotations for pneumonia.

          ## How to Use
          You can load this model using the `ultralytics` library:

          ```python
          from ultralytics import YOLO

          # Load the model directly from the Hugging Face Hub
          model = YOLO('jayanthapoojary1989/rsna-pneumonia-yolov8s/pytorch_yolov8_model.pt')

          # Perform inference on an image
          results = model('path/to/your/image.jpg')

          # Show results (displays image with detections)
          results[0].show() # Or for Colab: results[0].plot() and display with matplotlib

          Training Parameters (from this run)
          Base Model: YOLOv8s.pt
          Epochs Trained: 50 # Confirmed this is the correct way to get epochs
          Input Image Size: 640
          Batch Size: 16
          Evaluation Metrics (from validation set)
          Precision (Box): 0.5230
          Recall (Box): 0.6294
          [email protected] (Mean Average Precision at IoU 0.5): 0.5449 # Correct: No [0]
          [email protected]:0.95 (Mean Average Precision across IoU 0.5 to 0.95): 0.2168 # Correct: No [0]
          Disclaimer: This model is provided for research and educational purposes. Use in clinical settings requires rigorous validation, regulatory approval, and expert medical supervision.