i love you

app.py

@@ -44,6 +44,9 @@ transform = transforms.Compose([
 ])
 
 def predict(img):
+    if img is None:
+        return None
+    
     # Convert to PIL Image if needed
     if not isinstance(img, Image.Image):
         img = Image.fromarray(img)
@@ -54,25 +57,27 @@ def predict(img):
     # Get predictions
     with torch.no_grad():
         outputs = model(img)
-        probabilities = F.softmax(outputs, dim=1)
+        probabilities = F.softmax(outputs, dim=1)[0]
         
-    # Get top 3 predictions
-    probs, indices = torch.topk(probabilities, 3)
-    predictions = []
-    for prob, idx in zip(probs[0], indices[0]):
-        predictions.append((classes[idx], float(prob)))
+    # Create dictionary with all classes and their probabilities
+    predictions = {
+        classes[i]: float(probabilities[i]) * 100  # Convert to percentage
+        for i in range(len(classes))
+    }
+    
+    # Sort predictions by probability
+    sorted_predictions = dict(sorted(predictions.items(), key=lambda x: x[1], reverse=True))
     
-    # Format the results
-    return {pred[0]: pred[1] for pred in predictions}
+    return sorted_predictions
 
 # Create Gradio interface
 iface = gr.Interface(
     fn=predict,
     inputs=gr.Image(type="pil"),
-    outputs=gr.Label(num_top_classes=3),
+    outputs=gr.Label(num_top_classes=10),  # Show all 10 classes
     examples=[["example1.jpg"], ["example2.jpg"]],  # Optional: Add example images
     title="CIFAR-10 Image Classifier",
-    description="Upload an image to classify it into one of these categories: plane, car, bird, cat, deer, dog, frog, horse, ship, or truck"
+    description="Upload an image to classify it into one of these categories: plane, car, bird, cat, deer, dog, frog, horse, ship, or truck. Results show prediction confidence for all classes as percentages."
 )
 
 # Launch the app