Add app.py, model, and requirements

app.py

@@ -0,0 +1,55 @@
+import gradio as gr
+import torch
+from PIL import Image
+import io
+from ultralytics import YOLO
+
+# --- Load YOLO Model ---
+MODEL_PATH = 'model/char.pt'
+try:
+    model = YOLO(MODEL_PATH)
+    print(f"Model loaded successfully from: {MODEL_PATH}")
+except Exception as e:
+    print(f"Error loading model: {e}")
+    model = None
+
+# --- Prediction Function for Gradio ---
+def predict(image):
+    if model is None or image is None:
+        return None
+
+    try:
+        img = Image.fromarray(image).convert('RGB')
+        results = model(img)
+
+        predictions = []
+        for result in results:
+            for box in result.boxes:
+                x1, y1, x2, y2 = map(int, box.xyxy[0])
+                label = model.model.names[int(box.cls)]
+                confidence = float(box.conf[0])
+                predictions.append({'label': label, 'confidence': confidence, 'bbox': (x1, y1, x2, y2)})
+
+        # Draw bounding boxes on the image
+        draw = ImageDraw.Draw(img)
+        for pred in predictions:
+            x1, y1, x2, y2 = pred['bbox']
+            label = f"{pred['label']} ({pred['confidence']:.2f})"
+            draw.rectangle([x1, y1, x2, y2], outline="green", width=2)
+            draw.text((x1, y1 - 10), label, fill="red")
+
+        return img
+
+    except Exception as e:
+        return f"Error during prediction: {e}"
+
+# --- Gradio Interface ---
+iface = gr.Interface(
+    fn=predict,
+    inputs=gr.Image(label="Upload an Image"),
+    outputs=gr.Image(label="Image with Predictions"),
+    title="YOLO Object Detection",
+    description="Upload an image to see object detection predictions using a YOLO model.",
+)
+
+iface.launch()

model/char.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be71c61b3e156ac487d62313585facd7cd97123f861f955c168d7cca40ce9d5f
+size 19150547

requirements.txt.txt

@@ -0,0 +1,4 @@
+torch
+Pillow
+ultralytics
+gradio