Add README.md

README.md

@@ -0,0 +1,52 @@
+---
+library_name: ultralytics
+tags:
+- yolo
+- detection
+- document-analysis
+- pdf
+- question-segmentation
+datasets:
+- custom
+metrics:
+- mAP@50: 0.716
+- precision: 0.971
+pipeline_tag: object-detection
+license: mit
+---
+
+# YOLOv11m - Question Segmentation for PDFs
+
+A fine-tuned **YOLOv11m** model designed to detect and segment questions in Turkish educational documents (PDFs). 
+
+- **Task**: Object Detection
+- **Classes**: `question` (Single class)
+- **Resolution**: `1280` x `1280`
+
+## Model Details
+- **Base Model**: `yolo11m` (Ultralytics)
+- **Parameters**: ~20M
+- **Training Epochs**: 44
+- **Precision**: 0.971 (Very Low False Positives)
+- **mAP@50**: 0.716
+
+## Intended Use
+This model is optimized for extracting question blocks from dense test papers, worksheets, and exam booklets. It is robust to "background noise" (headers, isolated paragraphs) due to strict negative sampling during training.
+
+## Usage
+
+```python
+from ultralytics import YOLO
+
+# Load the model
+model = YOLO("hf://erayyapagci/yolo11m-question-segmentation")
+
+# Run Inference
+results = model("page_image.jpg", imgsz=1280, conf=0.25)
+
+# Show results
+results[0].show()
+```
+
+## Training Data
+Trained on a dataset of **14,693 images** (after strict filtering) sourced from 10 public Roboflow datasets. The data was split using **Document-Aware Splitting** to ensure no data leakage between training and validation sets.