Update app.py

app.py

@@ -1,37 +1,24 @@
-import gradio as gr
 from ultralytics import YOLO
-from PIL import Image, ImageDraw
-import numpy as np
-import torch
+import gradio as gr
+from PIL import Image
 
-# Load your existing YOLOv12 model
-model = YOLO("best.pt")
-model.to('cpu')  # force CPU
+# Load your trained YOLOv12 model from the repo
+model = YOLO("best.pt")  # just the file name if it's in the same folder as app.py
 
-# Inference function
-def detect_ear(image: Image.Image, conf: float = 0.25):
-    try:
-        img_array = np.array(image)
-        results = model(img_array, conf=conf, verbose=False)
-        annotated = results[0].plot()
-        return Image.fromarray(annotated)
-    except Exception as e:
-        # Show error text on image
-        im = image.copy()
-        draw = ImageDraw.Draw(im)
-        draw.text((10, 10), f"Error: {e}", fill="red")
-        return im
+# Define prediction function
+def predict(image):
+    results = model.predict(image)  # Run inference
+    annotated_img = results[0].plot()  # Draw boxes on image
+    return annotated_img
 
 # Gradio interface
 iface = gr.Interface(
-    fn=detect_ear,
-    inputs=[
-        gr.Image(type="pil", label="Upload Otoscopic Image"),
-        gr.Slider(0.0, 1.0, value=0.25, step=0.01, label="Confidence Threshold")
-    ],
-    outputs=gr.Image(type="pil", label="Detection Result"),
-    title="Automated Ear Disease Detection",
-    description="Detect ear conditions using YOLOv12 (CPU only)"
+    fn=predict,
+    inputs=gr.Image(type="pil"),
+    outputs=gr.Image(type="pil"),
+    title="Ear Condition Detection",
+    description="Upload an otoscopic image and get predictions from the trained YOLOv12 model."
 )
 
+# Launch the app
 iface.launch()