Update README.md

README.md

@@ -1,3 +1,171 @@
----
-license: mit
----
+---
+license: mit
+---
+Waste Classification - YOLOv8 Large (HighRes)
+
+🗑️ Model Summary
+
+This model is a fine-tuned version of YOLOv8 Large (yolov8l) designed for the detection and classification of 12 different types of waste materials. It was trained on high-resolution images (1280px) to capture fine details in trash objects.
+
+This project was developed by Kendrick as a Capstone Mini-Project for the REA AI Engineering Bootcamp.
+
+Model Architecture: YOLOv8-Large
+
+Task: Object Detection
+
+Input Resolution: 1280x1280
+
+Classes: 12
+
+🎯 Intended Use
+
+This model is intended to be used for:
+
+Automated waste sorting systems.
+
+Educational apps for recycling.
+
+Environmental monitoring.
+
+📊 Evaluation Results
+
+The model was evaluated on a validation set of 1,935 images.
+
+Metric
+
+Score
+
+Description
+
+mAP@50
+
+0.783
+
+Strong overall performance across all classes.
+
+Precision
+
+0.797
+
+High confidence in correct predictions.
+
+Recall
+
+0.733
+
+Good ability to find objects, though struggles with organic waste.
+
+mAP@50-95
+
+0.576
+
+High localization accuracy (bounding boxes are tight).
+
+Performance by Class
+
+The model excels at distinct rigid objects but struggles with amorphous organic matter.
+
+Class
+
+mAP@50
+
+Status
+
+Insight
+
+Clothes
+
+0.987
+
+🌟 Excellent
+
+Distinct shapes make this the easiest class.
+
+Brown-Glass
+
+0.905
+
+✅ Very Good
+
+Consistent texture and shape.
+
+Shoes
+
+0.847
+
+✅ Good
+
+High recall and precision.
+
+Plastic
+
+0.706
+
+⚠️ Moderate
+
+Struggles with transparency and deformation.
+
+Biological
+
+0.580
+
+❌ Needs Work
+
+High false negative rate.
+
+🔍 Deep Dive: Evaluation & Limitations
+
+Based on the Confusion Matrix analysis, the model demonstrates specific behaviors:
+
+The "Biological" Challenge:
+
+The model has a low Recall (0.445) for the biological class.
+
+Issue: It missed 741 instances of biological waste, misclassifying them as "Background".
+
+Reason: Biological waste (food scraps, leaves) lacks a defined shape compared to bottles or cans, blending into the background.
+
+False Positives:
+
+There are 540 instances where the model predicted biological waste on empty backgrounds. This suggests potential noise in the training labels or confusion with complex background textures.
+
+Background Confusion:
+
+The cardboard class also shows confusion with the background (159 false positives), likely due to color similarity with flooring/ground.
+
+⚙️ Training Configuration
+
+The model was trained on an NVIDIA A100-SXM4-40GB GPU for 6.26 hours.
+
+Epochs: 50
+
+Batch Size: 8
+
+Optimizer: AdamW (lr=0.000625)
+
+Image Size: 1280 (High Res)
+
+Augmentation: Standard YOLOv8 augmentations + Mosaic (disabled in last 10 epochs).
+
+💻 How to Use
+
+You can use this model with the Ultralytics Python library:
+
+from ultralytics import YOLO
+
+# Load the model
+model = YOLO("path/to/best.pt")
+
+# Perform inference on an image
+results = model("path/to/image.jpg")
+
+# Display results
+results[0].show()
+
+
+👨‍💻 Author
+
+Kendrick
+Alumni, REA AI Engineering Bootcamp
+
+This model card was generated based on training logs and evaluation charts.