Upload app.py

app.py

@@ -15,112 +15,86 @@ logger = logging.getLogger(__name__)
 MODEL_REPO = "Ahmedhassan54/Image-Classification"
 MODEL_FILE = "best_model.h5"
 
-# Download model from Hugging Face Hub
-def load_model_from_hf():
+# Initialize model to None
+model = None
+
+def load_model():
+    global model
     try:
-        logger.info("Attempting to load model...")
-        
-        # Check if model exists in cache
+        logger.info("⏳ Downloading model...")
         model_path = hf_hub_download(
             repo_id=MODEL_REPO,
             filename=MODEL_FILE,
             cache_dir=".",
-            force_download=True  # Ensure fresh download
+            force_download=True
         )
-        logger.info(f"Model downloaded to: {model_path}")
+        logger.info(f"📁 Model path: {model_path}")
         
-        # Load model
-        logger.info("Loading model...")
+        # Verify file exists
+        if not os.path.exists(model_path):
+            raise FileNotFoundError(f"Model file not found at {model_path}")
+            
+        logger.info("🔄 Loading TensorFlow model...")
         model = tf.keras.models.load_model(model_path)
-        logger.info("Model loaded successfully!")
-        return model
+        logger.info("✅ Model loaded successfully!")
         
     except Exception as e:
-        logger.error(f"Model loading failed: {str(e)}")
-        raise gr.Error(f"⚠️ Model loading failed: {str(e)}. Check the logs for details.")
+        logger.error(f"❌ Model loading failed: {str(e)}")
+        model = None
+        raise gr.Error(f"Model loading failed. Check logs for details.")
 
-# Load model when the app starts
-try:
-    model = load_model_from_hf()
-except Exception as e:
-    model = None
-    logger.error(f"Proceeding without model due to: {str(e)}")
+# Load model when app starts
+load_model()
 
 def classify_image(image):
     try:
-        logger.info("\nClassification started...")
-        
-        # Debug: Check input type
-        logger.info(f"Input type: {type(image)}")
-        
         if image is None:
-            raise ValueError("No image provided")
+            raise gr.Error("Please upload an image first")
+            
+        logger.info("🖼️ Processing image...")
         
-        # Convert image if needed
+        # Convert to PIL Image if numpy array
         if isinstance(image, np.ndarray):
-            logger.info("Converting numpy array to PIL Image")
             image = Image.fromarray(image)
-        elif not isinstance(image, Image.Image):
-            raise ValueError(f"Unexpected image type: {type(image)}")
-        
-        # Preprocess image
-        logger.info("Preprocessing image...")
+            
+        # Resize and normalize
         image = image.resize((150, 150))
-        image_array = np.array(image) / 255.0
-        
-        # Add batch dimension
-        if len(image_array.shape) == 3:
-            image_array = np.expand_dims(image_array, axis=0)
+        img_array = np.array(image) / 255.0
+        if len(img_array.shape) == 3:
+            img_array = np.expand_dims(img_array, axis=0)
+            
+        logger.info(f"📊 Input shape: {img_array.shape}")
         
-        logger.info(f"Image array shape: {image_array.shape}")
-        
-        # Make prediction
-        logger.info("Making prediction...")
         if model is None:
-            raise gr.Error("Model failed to load. Cannot make predictions.")
-        
-        prediction = model.predict(image_array, verbose=0)
-        logger.info(f"Raw prediction: {prediction}")
-        
-        confidence = float(prediction[0][0])
-        logger.info(f"Confidence score: {confidence}")
-        
-        # Format outputs
-        label_output = {
+            raise gr.Error("Model not loaded - using demo mode")
+            return {"Cat": 0.5, "Dog": 0.5}, pd.DataFrame({'Class': ['Cat', 'Dog'], 'Confidence': [0.5, 0.5]})
+            
+        pred = model.predict(img_array, verbose=0)
+        confidence = float(pred[0][0])
+        logger.info(f"🔮 Prediction confidence: {confidence}")
+        
+        results = {
             "Cat": round(1 - confidence, 4),
             "Dog": round(confidence, 4)
         }
         
-        # Create dataframe for bar plot
         plot_data = pd.DataFrame({
             'Class': ['Cat', 'Dog'],
             'Confidence': [1 - confidence, confidence]
         })
         
-        logger.info("Classification successful!")
-        logger.info(f"Results: {label_output}")
-        
-        return label_output, plot_data
+        return results, plot_data
         
     except Exception as e:
-        logger.error(f"Error during classification: {str(e)}", exc_info=True)
-        raise gr.Error(f"🔴 Classification failed: {str(e)}")
+        logger.error(f"💥 Classification error: {str(e)}")
+        raise gr.Error(f"Error processing image: {str(e)}")
 
-# Custom CSS
 css = """
-.gradio-container {
-    background: linear-gradient(to right, #f5f7fa, #c3cfe2);
-}
-footer {
-    visibility: hidden
-}
-.error-message {
-    color: red !important;
-    font-weight: bold !important;
-}
+.gradio-container { max-width: 900px; margin: auto; }
+footer { visibility: hidden; }
+.progress-bar { color: #ff4d4d !important; }
 """
 
-# Build the interface
 with gr.Blocks(css=css, theme=gr.themes.Soft()) as demo:
     gr.Markdown("""
     # 🐾 Cat vs Dog Classifier 🦮
@@ -131,23 +105,18 @@ with gr.Blocks(css=css, theme=gr.themes.Soft()) as demo:
         with gr.Column():
             image_input = gr.Image(label="Upload Image", type="pil")
             with gr.Row():
-                submit_btn = gr.Button("Classify", variant="primary")
-                clear_btn = gr.Button("Clear")
+                submit_btn = gr.Button("Classify 🚀", variant="primary")
+                clear_btn = gr.Button("Clear 🗑️")
         
         with gr.Column():
-            label_output = gr.Label(label="Predictions", num_top_classes=2)
+            label_output = gr.Label(label="Predictions")
             confidence_bar = gr.BarPlot(
                 pd.DataFrame({'Class': ['Cat', 'Dog'], 'Confidence': [0.5, 0.5]}),
-                x="Class",
-                y="Confidence",
-                y_lim=[0,1],
-                title="Confidence Scores",
-                width=400,
-                height=300,
-                container=False
+                x="Class", y="Confidence", y_lim=[0,1],
+                title="Confidence Scores", width=400, height=300
             )
     
-    # Example images
+    # Examples
     gr.Examples(
         examples=[
             ["https://upload.wikimedia.org/wikipedia/commons/1/15/Cat_August_2010-4.jpg"],
@@ -156,8 +125,7 @@ with gr.Blocks(css=css, theme=gr.themes.Soft()) as demo:
         inputs=image_input,
         outputs=[label_output, confidence_bar],
         fn=classify_image,
-        cache_examples=True,
-        label="Try these examples:"
+        cache_examples=True
     )
     
     # Button actions
@@ -165,16 +133,14 @@ with gr.Blocks(css=css, theme=gr.themes.Soft()) as demo:
         fn=classify_image,
         inputs=image_input,
         outputs=[label_output, confidence_bar],
-        api_name="classify"
+        api_name="predict"
     )
     
     clear_btn.click(
         fn=lambda: [None, pd.DataFrame({'Class': ['Cat', 'Dog'], 'Confidence': [0.5, 0.5]})],
         inputs=None,
-        outputs=[image_input, confidence_bar],
-        show_progress=False
+        outputs=[image_input, confidence_bar]
     )
 
-# Launch the app
 if __name__ == "__main__":
     demo.launch(debug=True)