Updated README.md

README.md

@@ -13,17 +13,44 @@ tags:
 
 ## Use Case
 
-## Evaluation Metrics
+This model is can be used for detecting humans from thermal images. This should work on both Pseudo-color and Grayscale thermal images. The model was fine tuned for humans only but can be finetuned further fort detecting other objects using Thermal images. 
 
-__Weights & Biases__: [Run Details](https://wandb.ai/2wb2ndur/Human-Detection-Thermal-Camera/runs/5j95496q/overview?workspace=user-2wb2ndur)
+To deploy this model use the following code:
 
-### Training Graphs
+- Install dependencies:
+```bash
+$ python -m pip install ultralytics supervision huggingface_hub 
+```
 
-![Training Graphs](./training_artifacts/results.png)
+- Python code
+```python
+# import libraries
+from huggingface_hub import hf_hub_download
+from ultralytics import YOLO
+from supervision import Detections
+import cv
+
+# download model
+model_path = hf_hub_download(
+    repo_id = "arnabdhar/YOLOv8-human-detection-thermal",
+    filename = "model.pt"
+)
+
+# load model
+model = YOLO(model_path)
+
+# method for inference
+def inference(image_path):
+    cv_image = cv.imread(image_path, cv2.IMREAD_ANYCOLOR)
+    model_output = model(cv_image, conf=0.6, verbose=False)
+    detections = Detections.from_ultralytics(model_output[0])
+    return detections
+```
 
 ## Training Code
 
 - Dataset Link: [Roboflow Universe](https://universe.roboflow.com/smart2/persondection-61bc2)
+- Weights & Biases: [Run Details](https://wandb.ai/2wb2ndur/Human-Detection-Thermal-Camera/runs/5j95496q/overview?workspace=user-2wb2ndur)
 
 ```python
 from ultralytics import YOLO