Update app.py

app.py

@@ -3,72 +3,90 @@ import sys
 import torch
 import gradio as gr
 from huggingface_hub import hf_hub_download, snapshot_download
+from pathlib import Path
 
-def setup_model():
-    # Download repository content
-    repo_path = snapshot_download(
-        repo_id="VLabTech/cognitive_net",
-        repo_type="model",
-        local_dir="./model_repo"
-    )
-    
-    # Add to Python path
-    sys.path.append(repo_path)
-    
-    # Now we can import from the downloaded modules
-    from memory import CognitiveMemory
-    from node import CognitiveNode
-    from network import DynamicCognitiveNet
-    
-    return DynamicCognitiveNet(input_size=5, output_size=2)
-
-def predict(input_text):
-    try:
-        # Parse input
-        values = [float(x.strip()) for x in input_text.split(",")]
-        if len(values) != 5:
-            return f"Error: Masukkan tepat 5 nilai (dipisahkan koma). Anda memasukkan {len(values)} nilai."
-        
-        # Setup model
-        model = setup_model()
+class CognitiveNetworkDemo:
+    def __init__(self):
+        self.model = None
+        self.repo_path = None
+        self.setup_environment()
         
-        # Generate prediction
-        input_tensor = torch.tensor(values, dtype=torch.float32)
-        output = model(input_tensor)
+    def setup_environment(self):
+        """Setup the environment and download the model"""
+        # Download repository content
+        self.repo_path = Path(snapshot_download(
+            repo_id="VLabTech/cognitive_net",
+            repo_type="model",
+            local_dir="./model_repo"
+        ))
         
-        # Format output
-        result = "Hasil Prediksi:\n"
-        result += f"Output 1: {output[0]:.4f}\n"
-        result += f"Output 2: {output[1]:.4f}"
-        
-        return result
-        
-    except ValueError as e:
-        return f"Error dalam format input: {str(e)}"
-    except Exception as e:
-        return f"Error: {str(e)}"
+        # Add model directory to Python path
+        if str(self.repo_path) not in sys.path:
+            sys.path.insert(0, str(self.repo_path))
+            
+    def load_model(self):
+        """Load the model if not already loaded"""
+        if self.model is None:
+            try:
+                # Import here to ensure path is set up
+                from model_repo.cognitive_net.network import DynamicCognitiveNet
+                self.model = DynamicCognitiveNet(input_size=5, output_size=2)
+            except ImportError as e:
+                raise ImportError(f"Gagal mengimpor model: {str(e)}")
+        return self.model
+
+    def predict(self, input_text):
+        """Make predictions using the model"""
+        try:
+            # Parse input
+            values = [float(x.strip()) for x in input_text.split(",")]
+            if len(values) != 5:
+                return f"Error: Masukkan tepat 5 nilai (dipisahkan koma). Anda memasukkan {len(values)} nilai."
+            
+            # Load model and generate prediction
+            model = self.load_model()
+            input_tensor = torch.tensor(values, dtype=torch.float32)
+            output = model(input_tensor)
+            
+            # Format output
+            result = "Hasil Prediksi:\n"
+            result += f"Output 1: {output[0]:.4f}\n"
+            result += f"Output 2: {output[1]:.4f}"
+            
+            return result
+            
+        except ValueError as e:
+            return f"Error dalam format input: {str(e)}"
+        except Exception as e:
+            return f"Error: {str(e)}"
 
-# Setup Gradio Interface
-demo = gr.Interface(
-    fn=predict,
-    inputs=gr.Textbox(
-        label="Input Values",
-        placeholder="Masukkan 5 nilai numerik (pisahkan dengan koma). Contoh: 1.0, 2.0, 3.0, 4.0, 5.0"
-    ),
-    outputs=gr.Textbox(label="Hasil Prediksi"),
-    title="Cognitive Network Demo",
-    description="""
-    ## Cognitive Network Inference Demo
-    Model ini menerima 5 input numerik dan menghasilkan 2 output numerik menggunakan
-    arsitektur Cognitive Network yang terinspirasi dari cara kerja otak biologis.
-    Model diambil dari VLabTech/cognitive_net.
-    """,
-    examples=[
-        ["1.0, 2.0, 3.0, 4.0, 5.0"],
-        ["0.5, -1.0, 2.5, 1.5, -0.5"],
-        ["0.1, 0.2, 0.3, 0.4, 0.5"]
-    ]
-)
+def main():
+    # Initialize the demo
+    demo_app = CognitiveNetworkDemo()
+    
+    # Setup Gradio Interface
+    demo = gr.Interface(
+        fn=demo_app.predict,
+        inputs=gr.Textbox(
+            label="Input Values",
+            placeholder="Masukkan 5 nilai numerik (pisahkan dengan koma). Contoh: 1.0, 2.0, 3.0, 4.0, 5.0"
+        ),
+        outputs=gr.Textbox(label="Hasil Prediksi"),
+        title="Cognitive Network Demo",
+        description="""
+        ## Cognitive Network Inference Demo
+        Model ini menerima 5 input numerik dan menghasilkan 2 output numerik menggunakan
+        arsitektur Cognitive Network yang terinspirasi dari cara kerja otak biologis.
+        Model diambil dari VLabTech/cognitive_net.
+        """,
+        examples=[
+            ["1.0, 2.0, 3.0, 4.0, 5.0"],
+            ["0.5, -1.0, 2.5, 1.5, -0.5"],
+            ["0.1, 0.2, 0.3, 0.4, 0.5"]
+        ]
+    )
+    
+    demo.launch()
 
 if __name__ == "__main__":
-    demo.launch()
+    main()