Upload app.py

app.py

@@ -43,6 +43,10 @@ class DogCatClassifier:
     
     def predict(self, image):
         try:
+            # Handle None input
+            if image is None:
+                return {"Please upload an image": 1.0}
+                
             # Preprocess image
             if isinstance(image, str):
                 image = Image.open(image).convert('RGB')
@@ -61,11 +65,12 @@ class DogCatClassifier:
                 dog_prob = probabilities[0][1].item()
                 
                 return {
-                    "Cat": cat_prob,
-                    "Dog": dog_prob
+                    "Cat": float(cat_prob),
+                    "Dog": float(dog_prob)
                 }
         except Exception as e:
-            return {"Error": 0.5, "Please try again": 0.5}
+            print(f"Error during prediction: {e}")
+            return {"Error - please try again": 1.0}
 
 # Initialize classifier
 classifier = DogCatClassifier()
@@ -76,48 +81,20 @@ def classify_image(image):
     """
     return classifier.predict(image)
 
-# Create Gradio interface with simpler components
-with gr.Blocks(title="🐱🐶 Cat vs Dog Classifier", theme=gr.themes.Soft()) as demo:
-    gr.Markdown("# 🐱🐶 Cat vs Dog Classifier")
-    gr.Markdown("Upload an image of a cat or dog, and the AI will classify it!")
-    gr.Markdown("*This model uses EfficientNet-B1 architecture trained on the Cats vs Dogs dataset.*")
-    
-    with gr.Row():
-        with gr.Column():
-            image_input = gr.Image(type="pil", label="Upload an image")
-            classify_btn = gr.Button("🔍 Classify Image", variant="primary")
-        
-        with gr.Column():
-            result_output = gr.Label(num_top_classes=2, label="Prediction Results")
-    
-    # Examples section
-    gr.Markdown("### Try these example images:")
-    example_images = [
-        ["test_images/cat1.jpg"],
-        ["test_images/cat2.jpg"], 
-        ["test_images/dog1.jpg"],
-        ["test_images/dog2.jpg"]
-    ]
-    gr.Examples(
-        examples=example_images,
-        inputs=image_input,
-        outputs=result_output,
-        fn=classify_image,
-        cache_examples=True
-    )
-    
-    # Event handlers
-    classify_btn.click(
-        fn=classify_image,
-        inputs=image_input,
-        outputs=result_output
-    )
+# Create simple Gradio interface
+demo = gr.Interface(
+    fn=classify_image,
+    inputs=gr.Image(type="pil", label="Upload an image of a cat or dog"),
+    outputs=gr.Label(num_top_classes=2, label="Prediction"),
+    title="🐱🐶 Cat vs Dog Classifier",
+    description="""
+    Upload an image of a cat or dog, and the AI will classify it!
     
-    image_input.change(
-        fn=classify_image,
-        inputs=image_input,
-        outputs=result_output
-    )
+    This model uses EfficientNet-B1 architecture trained on the classic Cats vs Dogs dataset.
+    Simply upload an image or drag and drop, then the prediction will appear automatically.
+    """,
+    theme="soft"
+)
 
 if __name__ == "__main__":
-    demo.launch(server_name="0.0.0.0", server_port=7860)
+    demo.launch()