Update README.md

README.md

@@ -21,21 +21,16 @@ This model detects and segments six types of vehicle damage: cracks, dents, glas
 
 ## Performance Metrics
 
-### Overall Performance
-| Task | Precision | Recall | mAP50 | mAP50-95 |
-|------|-----------|--------|-------|----------|
-| Box  | 0.753     | 0.689  | 0.734 | 0.513    |
-| Mask | 0.762     | 0.692  | 0.735 | 0.503    |
 
 ### Class-Specific Performance (Mask Segmentation)
-| Class         | Precision | Recall | mAP50 | mAP50-95 |
-|---------------|-----------|--------|-------|----------|
-| crack         | 0.665     | 0.368  | 0.445 | 0.167    |
-| dent          | 0.626     | 0.530  | 0.562 | 0.281    |
-| glass shatter | 0.881     | 1.000  | 0.986 | 0.724    |
-| lamp broken   | 0.759     | 0.825  | 0.857 | 0.669    |
-| scratch       | 0.684     | 0.560  | 0.589 | 0.284    |
-| tire flat     | 0.958     | 0.869  | 0.971 | 0.891    |
+       Class     Images  Instances      Box(P          R      mAP50  mAP50-95)     Mask(P          R      mAP50  mAP50-95)
+         all        571       1247      0.824       0.75      0.799      0.599      0.827      0.749      0.792      0.576
+       crack         92        152      0.657       0.48      0.545      0.322      0.665      0.483      0.518      0.214
+        dent        249        366      0.706      0.571      0.633      0.377      0.697       0.56      0.612      0.344
+glass shatter         89         91       0.98      0.989      0.994      0.728      0.981      0.989      0.994      0.784
+ lamp broken        103        103       0.91      0.893      0.964      0.791      0.921      0.902      0.967      0.808
+     scratch        281        482      0.728      0.614      0.676      0.421      0.734      0.613       0.68      0.368
+   tire flat         50         53      0.962      0.951      0.982      0.951      0.962      0.949      0.982      0.941
 
 ## Training Recipe
 
@@ -116,6 +111,62 @@ The model was trained on the CarDD (Car Damage Detection) dataset with:
 
 ## Usage
 
+
+Download weight: `!wget https://huggingface.co/harpreetsahota/car-dd-segmentation-yolov11/resolve/main/best.pt -O yolov11-seg-cardd.pt`
+
+```
+from ultralytics import YOLO
+import os
+import gdown
+
+# Load the model
+model = YOLO('best.pt')
+
+# Apply the model to the test dataset
+# FiftyOne automatically handles batching and processing
+test_dataset.apply_model(
+    model,
+    label_field="yolo_predictions",  # Field name to store predictions
+    confidence_thresh=0.25,          # Minimum confidence threshold
+    batch_size=8                     # Adjust based on your GPU memory
+)
+
+# Define the class list to match your model's classes
+classes = ["crack", "dent", "glass shatter", "lamp broken", "scratch", "tire flat"]
+
+# Evaluate detections against ground truth
+eval_results = test_dataset.evaluate_detections(
+    "yolo_predictions",              # Field containing model predictions  
+    gt_field="segmentations",        # Field containing ground truth
+    eval_key="model_eval",           # Key to store evaluation results
+    use_masks=True,                  # Use pixel masks for IoU calculation
+    compute_mAP=True,                # Compute mean Average Precision
+    method="coco",                   # COCO evaluation protocol
+    classes=classes,                 # Class list
+    iou=0.50                         # IoU threshold
+)
+
+# Print evaluation results
+print(eval_results)
+
+# Visualize evaluation results in the FiftyOne App
+from fiftyone import ViewField as F
+
+# Create a view showing false positives with high confidence
+high_conf_fp_view = test_dataset.filter_labels(
+    "yolo_predictions", 
+    (F("confidence") > 0.7) & (F("eval") == "fp")
+)
+
+# Sort by false positive count
+sorted_view = high_conf_fp_view.sort_by(
+    F("yolo_predictions.detections").length(), reverse=True
+)
+
+# Launch the app with this view
+session = fo.launch_app(sorted_view)
+```
+
 ## Limitations
 
 - Lower recall for crack detection (36.8%)