Update README.md
Browse files
README.md
CHANGED
|
@@ -52,6 +52,20 @@ YOLOv8 is a state-of-the-art object detection architecture, known for its speed
|
|
| 52 |
- **Training**: The model was trained using both `best.pt` (the best performing model during training) and `last.pt` (the final checkpoint).
|
| 53 |
- **Use Case**: Object detection and counting of cargo packages, forklifts, and trucks in warehouses, transportation hubs, or logistics centers.
|
| 54 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 55 |
## How to Use
|
| 56 |
|
| 57 |
You can load the model using the `ultralytics` library, as shown below:
|
|
|
|
| 52 |
- **Training**: The model was trained using both `best.pt` (the best performing model during training) and `last.pt` (the final checkpoint).
|
| 53 |
- **Use Case**: Object detection and counting of cargo packages, forklifts, and trucks in warehouses, transportation hubs, or logistics centers.
|
| 54 |
|
| 55 |
+
## Evaluation Results
|
| 56 |
+
|
| 57 |
+
The model was evaluated on the validation set using the following metrics:
|
| 58 |
+
|
| 59 |
+
| Metric | Value |
|
| 60 |
+
| ------------- | ------- |
|
| 61 |
+
| Precision | 0.77187 |
|
| 62 |
+
| Recall | 0.11111 |
|
| 63 |
+
| mAP50 | 0.09188 |
|
| 64 |
+
| mAP50-95 | 0.06383 |
|
| 65 |
+
| F1 Score | 0.19426 |
|
| 66 |
+
|
| 67 |
+
These metrics were obtained using a threshold of 0.5 for IoU (Intersection over Union).
|
| 68 |
+
|
| 69 |
## How to Use
|
| 70 |
|
| 71 |
You can load the model using the `ultralytics` library, as shown below:
|